© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1027
    Prev
    Next
    INDEX
    Explanations

    the word "instead" to indicate alternative choices or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Developer
    -0.71
    nostic
    -0.70
    topic
    -0.66
     kidding
    -0.64
    regon
    -0.64
    soever
    -0.64
    ッド
    -0.62
    exist
    -0.61
    OPLE
    -0.61
    ��
    -0.60
    POSITIVE LOGITS
     of
    0.79
     Of
    0.77
    idad
    0.74
     OF
    0.70
    ide
    0.67
    um
    0.64
    .–
    0.64
    itan
    0.64
    of
    0.64
    orted
    0.63
    Activations Density 0.015%

    No Known Activations