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

    Neuronpedia

    INDEX
    Explanations

    words related to repetitive patterns or sequences, often involving a series of events or actions that occur in a cyclical manner

    oai_token-act-pair · gpt-3.5-turbo

    references to cycles or cyclical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.95
    orage
    -0.90
    imus
    -0.89
    amina
    -0.82
    essors
    -0.81
    imates
    -0.77
     Aires
    -0.75
    alty
    -0.75
    oaded
    -0.75
    anamo
    -0.73
    POSITIVE LOGITS
     cycle
    0.94
     erg
    0.91
    cycle
    0.83
    cles
    0.83
     repeats
    0.78
     Cycle
    0.74
    chron
    0.74
    dayName
    0.73
     cycles
    0.71
     Delay
    0.71
    Act Density 0.043%

    No Known Activations