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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning various organizations and their statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.76
     transgress
    -0.65
     generations
    -0.62
    lust
    -0.62
    Availability
    -0.59
     intensity
    -0.58
    actual
    -0.57
     eligibility
    -0.57
    fall
    -0.57
     gust
    -0.55
    POSITIVE LOGITS
    76561
    0.84
    otos
    0.78
     wrote
    0.75
     congratulated
    0.74
     commented
    0.71
     agrees
    0.70
     urged
    0.70
    told
    0.70
     advises
    0.68
    achu
    0.67
    Act Density 0.179%

    No Known Activations