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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases that convey skepticism or critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagext
    -0.64
     unless
    -0.59
     except
    -0.56
    unless
    -0.55
    writeFieldEnd
    -0.54
     Clu
    -0.54
    PerformLayout
    -0.54
     estekak
    -0.54
     kecuali
    -0.53
    JpaRepository
    -0.53
    POSITIVE LOGITS
     certainly
    0.89
     keineswegs
    0.82
    certainly
    0.79
     Certainly
    0.79
    Certainly
    0.73
    決して
    0.73
     definitely
    0.67
     keines
    0.65
     obviously
    0.63
     ciertamente
    0.62
    Act Density 0.167%

    No Known Activations