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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific timing events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to timing or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inis
    -0.88
    undy
    -0.86
    tained
    -0.78
    vasive
    -0.74
    alion
    -0.72
    ieves
    -0.72
    deen
    -0.70
    riel
    -0.70
    iliary
    -0.69
    irie
    -0.69
    POSITIVE LOGITS
     timing
    0.92
     cooker
    0.78
     reversal
    0.76
     timed
    0.73
     lapse
    0.71
     inacc
    0.70
     permitting
    0.70
     pulses
    0.70
     sensitive
    0.69
     charm
    0.68
    Act Density 0.030%

    No Known Activations