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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "what do" or related phrases seeking opinions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.71
     ISNI
    -0.70
    ſelf
    -0.68
    ^(@)
    -0.67
     وتسجيلات
    -0.66
     itſelf
    -0.65
     Efq
    -0.63
     afp
    -0.59
     ་་
    -0.59
    httphttps
    -0.59
    POSITIVE LOGITS
    RegressionTest
    0.70
     tưởng
    0.58
    aczy
    0.56
     what
    0.52
     aspetta
    0.52
    InvalidProtocol
    0.52
    Abit
    0.52
    Sapp
    0.52
     textes
    0.51
     balas
    0.50
    Act Density 0.066%

    No Known Activations