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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures related to rankings or prevalence in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.84
    abestanden
    -0.83
     houſe
    -0.77
    spesies
    -0.77
    loài
    -0.76
     '\\;'
    -0.76
     ſtre
    -0.75
     ſtate
    -0.75
     himſelf
    -0.74
     ſtand
    -0.74
    POSITIVE LOGITS
    仕方
    0.52
    Билгалдахарш
    0.49
    CloseOperation
    0.47
    oa̍t
    0.46
     legen
    0.46
    ViewImports
    0.43
    效
    0.42
    zarchiwizowane
    0.40
     O
    0.40
    Howdy
    0.40
    Act Density 0.022%

    No Known Activations