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

    Neuronpedia

    INDEX
    Explanations

    locations or specific points in time

    oai_token-act-pair · gpt-3.5-turbo

    instances of time references in the context of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.65
    tip
    -0.63
    accompanied
    -0.62
    Eva
    -0.62
    ãĥ©ãĥ³
    -0.59
    tal
    -0.58
     Converted
    -0.58
    fan
    -0.57
     underdog
    -0.56
     Travels
    -0.56
    POSITIVE LOGITS
     anymore
    1.76
     nor
    1.69
     slightest
    1.28
     whatsoever
    1.24
    nor
    1.14
     any
    1.08
     anywhere
    1.00
     either
    0.98
     Nor
    0.96
     anybody
    0.93
    Act Density 0.482%

    No Known Activations