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

    Neuronpedia

    INDEX
    Explanations

    accounts of events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "what happened" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mens
    -0.87
    ierre
    -0.82
    hart
    -0.78
    ament
    -0.77
    cius
    -0.76
    urat
    -0.75
    tesy
    -0.74
    orthy
    -0.74
    inently
    -0.73
    artisan
    -0.72
    POSITIVE LOGITS
     unfolding
    0.87
     Happ
    0.83
     transpired
    0.80
     wrong
    0.78
     unfold
    0.77
     Ambro
    0.76
    âĹ¼
    0.70
     Kardash
    0.70
     happened
    0.69
     happen
    0.69
    Act Density 0.036%

    No Known Activations