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

    Neuronpedia

    INDEX
    Explanations

    instances of perception verbs indicating seeing or hearing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prof
    -0.18
    à¥įतव
    -0.16
    樣
    -0.15
    onde
    -0.15
    ãĥ³ãĤº
    -0.15
     fond
    -0.15
     source
    -0.15
    immel
    -0.14
    ogene
    -0.14
    .codehaus
    -0.14
    POSITIVE LOGITS
    (EXPR
    0.16
    ovny
    0.15
     Mana
    0.15
    aryana
    0.15
    quia
    0.14
    oom
    0.14
     ÅĻÃŃj
    0.14
    ifecycle
    0.14
    anten
    0.14
    uae
    0.14
    Act Density 0.083%

    No Known Activations