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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spreading information or messages to others

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to disseminating information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.82
    etary
    -0.63
    onding
    -0.63
    ļéĨĴ
    -0.61
    ski
    -0.58
    orts
    -0.58
    ishes
    -0.57
    cients
    -0.57
    efe
    -0.56
    ORTS
    -0.56
    POSITIVE LOGITS
    fitted
    1.07
    wards
    0.93
    sole
    0.92
    stretched
    0.91
     loud
    0.89
    smart
    0.88
    skirts
    0.83
    lived
    0.83
    bur
    0.81
     Loud
    0.79
    Act Density 0.085%

    No Known Activations