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

    Neuronpedia

    INDEX
    Explanations

    mentions of repeated or cyclical events or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cycle" and its various contexts in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gould
    -0.71
    utf
    -0.70
     Vernon
    -0.70
    essors
    -0.67
    jp
    -0.66
    interested
    -0.66
     Canad
    -0.64
     lingu
    -0.63
    aii
    -0.63
    wered
    -0.63
    POSITIVE LOGITS
     cycle
    4.23
     Cycle
    3.22
     cycles
    3.16
    cycle
    2.58
    cycles
    2.06
     cycling
    1.67
     cycl
    1.59
    Cy
    1.39
     Cycling
    1.20
     cascade
    1.19
    Act Density 0.024%

    No Known Activations