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

    Neuronpedia

    INDEX
    Explanations

    phrases related to endings or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with endings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledged
    -0.73
    iors
    -0.72
    rouse
    -0.69
    Recommended
    -0.68
     WATCHED
    -0.66
    opol
    -0.65
    uyomi
    -0.64
    Prior
    -0.63
    ickr
    -0.62
    ync
    -0.61
    POSITIVE LOGITS
     reckoning
    0.87
     goodbye
    0.85
     hostilities
    0.81
     humankind
    0.76
     farewell
    0.73
     mankind
    0.71
     havoc
    0.71
     patience
    0.69
     civilization
    0.68
     humanity
    0.68
    Act Density 0.139%

    No Known Activations