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

    Neuronpedia

    INDEX
    Explanations

    the word "once" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to events or actions that occur repeatedly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.73
    alf
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.72
    RIC
    -0.72
     âĸº
    -0.70
    urga
    -0.70
    NRS
    -0.70
    rug
    -0.69
    LCS
    -0.69
    Í
    -0.69
    POSITIVE LOGITS
    soever
    0.83
     again
    0.80
     bitten
    0.77
     Upon
    0.76
    falls
    0.71
    handedly
    0.68
     mastered
    0.68
     glimps
    0.67
     tasted
    0.65
     upon
    0.64
    Act Density 0.023%

    No Known Activations