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

    Neuronpedia

    INDEX
    Explanations

    words related to negative or extreme adjectives

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and terms related to negative or problematic qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.72
    Reviewer
    -0.68
     Angels
    -0.63
     Blacks
    -0.63
    stones
    -0.59
    tops
    -0.58
     ecstasy
    -0.58
     Jackets
    -0.58
     ashes
    -0.57
     Balls
    -0.56
    POSITIVE LOGITS
    cedented
    0.99
    achable
    0.81
    ivable
    0.81
    itable
    0.79
    iable
    0.78
    izable
    0.78
    isable
    0.77
    vised
    0.75
    ended
    0.75
    icable
    0.73
    Act Density 0.101%

    No Known Activations