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

    Neuronpedia

    INDEX
    Explanations

    specific dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative opinions or statements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.83
    .","
    -0.82
    Engineers
    -0.69
    )</
    -0.64
    .</
    -0.63
    dq
    -0.60
    .''
    -0.59
    Always
    -0.59
    sed
    -0.58
    \">
    -0.57
    POSITIVE LOGITS
     irony
    0.80
     hypocrisy
    0.79
     Chaff
    0.74
     redacted
    0.71
     Tsarnaev
    0.71
     politic
    0.70
     Chomsky
    0.70
     Manafort
    0.69
     Lavrov
    0.69
     outraged
    0.68
    Act Density 1.380%

    No Known Activations