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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 958
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" in various contexts

    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
    ��
    -0.83
    selves
    -0.74
    chel
    -0.72
    ellen
    -0.71
    asured
    -0.69
    jong
    -0.68
    gently
    -0.66
    vich
    -0.66
    ruary
    -0.66
    NER
    -0.66
    POSITIVE LOGITS
     recess
    0.74
     voic
    0.70
     footage
    0.65
    letes
    0.62
     lengths
    0.61
     conception
    0.61
     Bas
    0.60
    ampa
    0.60
    asts
    0.59
    ombo
    0.59
    Activations Density 0.062%

    No Known Activations