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

    Neuronpedia

    INDEX
    Explanations

    proper nouns occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    tokens related to proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elig
    -0.76
     Bundes
    -0.68
     descend
    -0.68
     opio
    -0.66
     sugg
    -0.65
     Babel
    -0.63
     sqor
    -0.61
     dehydration
    -0.61
     jud
    -0.61
     hallucinations
    -0.60
    POSITIVE LOGITS
    igans
    0.90
    nikov
    0.89
    vana
    0.84
    igham
    0.80
    chenko
    0.79
    utical
    0.77
    bug
    0.75
    ucket
    0.73
    grass
    0.72
    bugs
    0.72
    Act Density 0.104%

    No Known Activations