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

    Neuronpedia

    INDEX
    Explanations

    words related to problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    m
    -1.86
    м
    -1.13
    م
    -1.13
    mā
    -0.81
    mide
    -0.81
    mido
    -0.75
    mą
    -0.71
    mbe
    -0.66
    mte
    -0.65
    mpo
    -0.64
    POSITIVE LOGITS
    requireNonNull
    0.38
     Administrativna
    0.37
    ⓧ
    0.34
    ConverterFactory
    0.33
    sproz
    0.32
    IsMutable
    0.31
    transQ
    0.31
    iastical
    0.30
     Proz
    0.30
     tránh
    0.29
    Act Density 0.430%

    No Known Activations