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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication, particularly instances where individuals are talking to each other

    oai_token-act-pair · gpt-3.5-turbo

    the act of communicating or talking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.69
     ILCS
    -0.66
    gradation
    -0.65
    fighter
    -0.63
    chwitz
    -0.61
    owa
    -0.61
    amins
    -0.60
    edition
    -0.60
    wcsstore
    -0.60
    ynski
    -0.60
    POSITIVE LOGITS
     him
    0.86
     strangers
    0.77
     reporters
    0.76
     us
    0.71
     them
    0.71
     representatives
    0.71
    è¦ļéĨĴ
    0.70
     assistants
    0.69
     passers
    0.68
     outsiders
    0.67
    Act Density 0.080%

    No Known Activations