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

    Neuronpedia

    INDEX
    Explanations

    technical terms and methods related to file and input/output operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TH
    -0.15
    boost
    -0.15
    seg
    -0.15
    coop
    -0.15
    amburger
    -0.14
    inker
    -0.14
    rou
    -0.13
    itter
    -0.13
    иÑĤÑĮ
    -0.13
    rov
    -0.13
    POSITIVE LOGITS
    orelease
    0.16
    çĽijåIJ¬é¡µéĿ¢
    0.15
    Ïĥή
    0.15
     Hearts
    0.14
    ROTO
    0.14
     Cosmos
    0.14
     Dün
    0.14
    _compat
    0.14
    ÅĻeh
    0.14
     ë¦
    0.14
    Act Density 0.070%

    No Known Activations