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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disciplinary actions or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    actions involving failure to comply with rules or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endif
    -0.77
    ciating
    -0.73
    depending
    -0.71
    inger
    -0.68
    fortunately
    -0.68
    gradation
    -0.67
    erm
    -0.66
    cking
    -0.66
    assuming
    -0.65
    atari
    -0.65
    POSITIVE LOGITS
     sake
    0.87
     illegal
    0.79
     improper
    0.76
     purposes
    0.73
     nonviolent
    0.64
     unlawful
    0.63
     insensitive
    0.63
    tein
    0.62
     withd
    0.62
     unsafe
    0.62
    Act Density 0.162%

    No Known Activations