Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the benefits or drawbacks of actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.15
    ationale
    -0.15
    issen
    -0.15
    bare
    -0.14
    ÏĩÏī
    -0.14
    ancy
    -0.14
    gue
    -0.14
    chie
    -0.14
    .SaveChangesAsync
    -0.14
     moc
    -0.14
    POSITIVE LOGITS
     morale
    0.16
    abl
    0.16
    ãĥ¼ãĥį
    0.16
    Escort
    0.15
     finances
    0.15
    اخ
    0.14
     Blank
    0.14
    zers
    0.14
    FixedSize
    0.14
     reput
    0.14
    Act Density 0.073%

    No Known Activations