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

    Neuronpedia

    INDEX
    Explanations

    comparisons and preferences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Etc
    -0.67
    acek
    -0.60
    cterms
    -0.58
     Etc
    -0.58
    gino
    -0.58
    COMPARE
    -0.56
    arranty
    -0.56
    derr
    -0.56
    رش
    -0.56
    nische
    -0.55
    POSITIVE LOGITS
    Datuak
    0.84
    InjectAttribute
    0.79
    BeginContext
    0.74
    ConstraintMaker
    0.71
    StoreMessageInfo
    0.71
    UnusedPrivate
    0.69
     оригіналу
    0.68
     *)__
    0.67
    oa̍t
    0.65
    writeFieldEnd
    0.63
    Act Density 1.050%

    No Known Activations