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

    Neuronpedia

    INDEX
    Explanations

    words related to cycling or repetitive processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of cycles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essors
    -0.83
    urion
    -0.80
    roit
    -0.79
    ever
    -0.75
    enton
    -0.75
    ifice
    -0.73
    orage
    -0.72
    paid
    -0.72
    obby
    -0.71
    eared
    -0.71
    POSITIVE LOGITS
     cycle
    1.33
     Cycle
    1.28
     cycles
    1.13
    cycles
    1.12
    cycle
    1.11
     CY
    0.93
     erg
    0.71
     Era
    0.71
    cles
    0.71
     Frie
    0.70
    Act Density 0.011%

    No Known Activations