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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or criteria for accessing resources or support

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Majefty
    -0.86
    NUMX
    -0.79
     auffi
    -0.79
     Reſ
    -0.79
    ſelf
    -0.77
     betweenstory
    -0.77
    MessageTagHelper
    -0.76
     purpoſe
    -0.76
    таратура
    -0.75
     disambiguazione
    -0.75
    POSITIVE LOGITS
     lucky
    0.50
    label
    0.45
    幸运
    0.45
     label
    0.45
     fortunate
    0.44
    Label
    0.44
     $\
    0.42
     suerte
    0.42
     dispositif
    0.41
     Ma
    0.40
    Act Density 0.312%

    No Known Activations