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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns used in statements related to responsibility or actions taken by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maxn
    -0.69
     referenties
    -0.65
     ostavi
    -0.63
     surla
    -0.62
     autorytatywna
    -0.59
     scopri
    -0.58
     femininas
    -0.55
    iettivo
    -0.55
    ovico
    -0.55
     NDEBUG
    -0.54
    POSITIVE LOGITS
    LookAnd
    0.56
     protoimpl
    0.56
    لیس
    0.55
    scriptcase
    0.55
    principalTable
    0.53
    CppMethod
    0.53
    setPreferred
    0.53
    Referències
    0.53
     Solitude
    0.53
     malin
    0.51
    Act Density 0.306%

    No Known Activations