© 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. 1352
    Prev
    Next
    INDEX
    Explanations

    words related to movement or travel

    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
    axis
    -0.72
    aca
    -0.68
    iciency
    -0.68
    iott
    -0.67
    leck
    -0.67
    arrell
    -0.65
    ectomy
    -0.65
    bugs
    -0.64
    ickers
    -0.64
     Aires
    -0.63
    POSITIVE LOGITS
     toward
    0.84
     towards
    0.83
     into
    0.82
     straight
    0.80
     INTO
    0.80
    ��
    0.74
    �
    0.71
    */(
    0.70
     forward
    0.68
    イト
    0.68
    Activations Density 0.019%

    No Known Activations