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

    Neuronpedia

    INDEX
    Explanations

    instances of specific times or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to occurrences or instances related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teasp
    -0.71
    ometimes
    -0.70
    haar
    -0.70
    dale
    -0.69
    ãĤ´ãĥ³
    -0.68
    ocobo
    -0.68
    ottesville
    -0.68
    inders
    -0.67
    urrection
    -0.66
     exting
    -0.65
    POSITIVE LOGITS
     anyone
    1.01
     that
    0.92
     anybody
    0.90
     ever
    0.87
     someone
    0.87
     since
    0.86
     they
    0.84
     we
    0.83
     EVER
    0.80
     foreigners
    0.74
    Act Density 0.046%

    No Known Activations