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

    Neuronpedia

    INDEX
    Explanations

    adjectives with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    words related to ominous or threatening contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.91
    llan
    -0.76
     Leilan
    -0.72
    king
    -0.70
    £ı
    -0.66
    oning
    -0.65
    llor
    -0.64
    plane
    -0.64
    ĨĴ
    -0.63
     Thousand
    -0.61
    POSITIVE LOGITS
    ations
    0.93
    ious
    0.89
    atory
    0.88
    iless
    0.83
    omin
    0.82
    iously
    0.81
    OWER
    0.81
    osite
    0.72
    ãĥ³ãĤ¸
    0.72
    ptives
    0.71
    Act Density 0.051%

    No Known Activations