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

    Neuronpedia

    INDEX
    Explanations

    references to degrees of murder in legal contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     affichés
    -0.48
    Cris
    -0.45
     Rady
    -0.45
    았
    -0.45
    unft
    -0.44
    ospel
    -0.44
     szóci
    -0.44
     ROC
    -0.43
     secco
    -0.43
    fromCharCode
    -0.42
    POSITIVE LOGITS
    #
    0.84
    曖昧さ回避
    0.73
     الحره
    0.69
    fromnode
    0.69
     مشين
    0.68
     الدولى
    0.68
    Jeografia
    0.67
    yarnpkg
    0.67
     المعيارى
    0.66
    bkz
    0.65
    Act Density 0.004%

    No Known Activations