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

    Neuronpedia

    INDEX
    Explanations

    references to missing items or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skins
    -0.18
    antan
    -0.17
    leasing
    -0.15
    antar
    -0.14
    s
    -0.14
    sar
    -0.14
     NavParams
    -0.14
    viso
    -0.14
    ffee
    -0.14
    sz
    -0.13
    POSITIVE LOGITS
    足
    0.15
    /loose
    0.14
    ivement
    0.14
    /problem
    0.14
    letal
    0.14
    ades
    0.14
    ellaneous
    0.14
    eniable
    0.13
    missing
    0.13
    ocks
    0.13
    Act Density 0.030%

    No Known Activations