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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of events or sequences of events in a series of texts

    oai_token-act-pair · gpt-3.5-turbo

    references to significant occurrences or happenings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzi
    -0.72
    geon
    -0.70
    ench
    -0.70
    Äĩ
    -0.69
    berman
    -0.69
    acked
    -0.69
    wall
    -0.68
    artisan
    -0.68
    ression
    -0.66
     Canal
    -0.64
    POSITIVE LOGITS
     transpired
    1.14
     unfold
    1.08
     unfolded
    1.08
     unfolding
    1.06
     events
    0.99
    hips
    0.96
     occurring
    0.93
    uate
    0.91
     happening
    0.88
    uating
    0.87
    Act Density 0.025%

    No Known Activations