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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»iji
    -0.16
    راÙĨ
    -0.15
    leen
    -0.15
     Hoch
    -0.15
    enu
    -0.15
    untas
    -0.14
    outine
    -0.14
    picture
    -0.14
    orne
    -0.14
     mist
    -0.14
    POSITIVE LOGITS
    ãģĪãģ°
    0.16
    egral
    0.15
    ayne
    0.15
    AccessorType
    0.14
    phinx
    0.14
     annex
    0.14
    heck
    0.14
    جÙħ
    0.13
     ÑĩеÑĢ
    0.13
    åľ¨çº¿è§Ĥçľĭ
    0.13
    Act Density 0.232%

    No Known Activations