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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of "first" in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the introduction or initial occurrence of concepts, terms, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blast
    -0.72
    contin
    -0.71
    still
    -0.67
    interrupted
    -0.66
    mble
    -0.64
    ilation
    -0.63
     perpetual
    -0.60
    ros
    -0.60
    pering
    -0.60
    vic
    -0.60
    POSITIVE LOGITS
     estab
    0.72
    APH
    0.72
    eared
    0.71
     Pwr
    0.69
    arthed
    0.65
    20439
    0.65
    schild
    0.65
    oké
    0.64
     Te
    0.62
     Alto
    0.61
    Act Density 0.178%

    No Known Activations