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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to a negative or unwanted context

    oai_token-act-pair · gpt-3.5-turbo

    terms that denote significant or problematic qualities and categories in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.70
    veyard
    -0.70
    xual
    -0.67
    swer
    -0.66
    uana
    -0.63
    mma
    -0.63
    KN
    -0.62
     Myster
    -0.61
    Thumbnail
    -0.60
    agame
    -0.59
    POSITIVE LOGITS
     amounts
    0.92
     portions
    0.89
     quantities
    0.88
     burdens
    0.83
     messages
    0.82
     objects
    0.82
     passages
    0.78
     segments
    0.77
     items
    0.77
     copies
    0.77
    Act Density 0.445%

    No Known Activations