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

    Neuronpedia

    INDEX
    Explanations

    words related to negative connotations or obscurities

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the concept of "ominous" or negative foreboding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.85
    llan
    -0.77
     Leilan
    -0.69
    £ı
    -0.64
    king
    -0.63
     Sparrow
    -0.61
    wan
    -0.60
     Immunity
    -0.59
     thickness
    -0.59
    spin
    -0.58
    POSITIVE LOGITS
    ations
    1.14
    atory
    1.09
    omin
    1.09
    ational
    1.03
    ator
    1.02
    ATIONS
    1.01
    ators
    1.00
    atorial
    0.98
    atus
    0.97
    uously
    0.95
    Act Density 0.027%

    No Known Activations