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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" or its variations, indicating conversations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.63
    MLLoader
    -0.63
    Portale
    -0.62
    yti
    -0.61
    FXMLLoader
    -0.61
    googleapis
    -0.61
    ıyordu
    -0.61
    tığı
    -0.61
    Personensuche
    -0.60
    antoms
    -0.59
    POSITIVE LOGITS
     talked
    3.47
     talking
    3.23
    talking
    2.77
     talk
    2.75
     Talking
    2.68
    Talking
    2.63
    talk
    2.52
     TALK
    2.47
     talks
    2.47
     Talk
    2.36
    Act Density 0.080%

    No Known Activations