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

    Neuronpedia

    INDEX
    Explanations

    instances of essential verbs and conjunctions indicating potential outcomes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤал
    -0.15
     Smarty
    -0.15
    abe
    -0.14
     Streets
    -0.14
    stal
    -0.14
    emey
    -0.14
     Scatter
    -0.13
    ãn
    -0.13
    _SECURITY
    -0.13
    .timedelta
    -0.13
    POSITIVE LOGITS
    olley
    0.15
    oley
    0.14
    ç«ĭãģ¦
    0.14
    ĥĿ
    0.14
    erable
    0.14
    eka
    0.14
     GR
    0.14
    amin
    0.14
     Kear
    0.13
    efore
    0.13
    Act Density 0.000%

    No Known Activations