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

    Neuronpedia

    INDEX
    Explanations

    phrases related to verbal communication and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to conversations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    necess
    -0.69
     thirds
    -0.69
    azo
    -0.66
     Invalid
    -0.66
    borne
    -0.59
     {*
    -0.59
    ARA
    -0.59
    izzard
    -0.58
    resource
    -0.58
    emis
    -0.58
    POSITIVE LOGITS
     talk
    3.59
    talk
    2.75
     Talk
    2.47
    Talk
    2.26
     talks
    1.93
    talking
    1.85
     discuss
    1.85
     talking
    1.83
     speak
    1.77
     talked
    1.77
    Act Density 0.019%

    No Known Activations