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

    Neuronpedia

    INDEX
    Explanations

    statistics and figures

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to political events or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.64
     Allaah
    -0.55
    -->
    -0.55
    .</
    -0.54
    ...)
    -0.54
    `.
    -0.54
    .","
    -0.54
    Allah
    -0.53
     ``(
    -0.52
    .<
    -0.51
    POSITIVE LOGITS
     meanwhile
    0.66
    odore
    0.59
    endum
    0.52
     Jacobs
    0.48
    ccording
    0.47
     irony
    0.47
     however
    0.46
     Lauder
    0.46
     responded
    0.46
     aback
    0.45
    Act Density 1.792%

    No Known Activations