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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ter" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.70
    ¬¼
    -0.66
     disparate
    -0.65
     Palestin
    -0.65
    Ĥ¬
    -0.65
    uncture
    -0.63
    Ĭ±
    -0.63
    ELS
    -0.62
     precaution
    -0.62
     Pace
    -0.61
    POSITIVE LOGITS
    geist
    1.22
    ranean
    1.13
    rors
    1.05
    rible
    0.98
    rane
    0.97
    tainment
    0.89
    brate
    0.89
    brates
    0.84
    restrial
    0.84
    ribly
    0.83
    Act Density 0.016%

    No Known Activations