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

    Neuronpedia

    INDEX
    Explanations

    specific events or actions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    significant events and actions related to contests, conflicts, or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.73
     Travels
    -0.65
    Join
    -0.64
     Flavoring
    -0.63
    pport
    -0.62
     Recent
    -0.61
     recent
    -0.60
     Availability
    -0.60
    fts
    -0.56
    Recent
    -0.56
    POSITIVE LOGITS
     lasted
    1.78
     consisted
    1.72
     resulted
    1.70
     culminated
    1.62
     coincided
    1.53
     yielded
    1.51
     amounted
    1.49
     became
    1.47
     ended
    1.46
     seemed
    1.46
    Act Density 0.590%

    No Known Activations