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

    Neuronpedia

    INDEX
    Explanations

    words related to repetitive or recurring actions or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recurring roles or themes within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chens
    -0.84
    ablishment
    -0.78
    yer
    -0.77
    eah
    -0.77
    imb
    -0.73
    okin
    -0.72
    ugen
    -0.71
    cellence
    -0.70
    umenthal
    -0.70
    IDA
    -0.69
    POSITIVE LOGITS
     recurring
    1.22
     recurrent
    0.99
     nightmares
    0.98
     subsequ
    0.97
     themes
    0.94
     episodes
    0.93
     occurrences
    0.90
     bouts
    0.90
     motif
    0.89
    interstitial
    0.87
    Act Density 0.009%

    No Known Activations