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

    Neuronpedia

    INDEX
    Explanations

    truthful and honest descriptions of experiences or items

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    '],'
    -0.52
    texttt
    -0.50
    rungsseite
    -0.50
    ✭✭
    -0.49
    Билгалдахарш
    -0.48
     Bun
    -0.47
     Hecht
    -0.46
     Sad
    -0.42
     sam
    -0.42
    ()])
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.71
    ぐれ
    0.70
     proposés
    0.69
    oa̍t
    0.69
     ainfi
    0.68
     Shakspeare
    0.68
     étoit
    0.67
    NUMX
    0.67
     profonde
    0.66
    ScopeManager
    0.66
    Act Density 0.074%

    No Known Activations