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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to qualities like reliability, danger, provocation, and cleanliness

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to quality and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾į
    -0.80
     Parables
    -0.73
    ©¶æ
    -0.69
    eper
    -0.66
     Lawyers
    -0.64
     Volcano
    -0.62
    cano
    -0.62
     Unch
    -0.60
    acci
    -0.60
    atus
    -0.59
    POSITIVE LOGITS
     minded
    0.65
    advertising
    0.64
     visionary
    0.64
     alike
    0.63
    itud
    0.63
    rous
    0.63
    istic
    0.63
     sibling
    0.62
     editions
    0.62
    yright
    0.62
    Act Density 0.192%

    No Known Activations