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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and entities, particularly in a political or financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.65
     Originally
    -0.64
    atile
    -0.60
    aples
    -0.58
     Gibbs
    -0.54
    perature
    -0.53
    itars
    -0.52
    ccording
    -0.51
     Osw
    -0.51
    Ĭ±
    -0.51
    POSITIVE LOGITS
    `.
    0.83
    .</
    0.73
    !".
    0.70
    '.
    0.68
    ?".
    0.66
    "!
    0.65
    .''
    0.64
    .'
    0.63
    ''.
    0.63
    ULTS
    0.62
    Act Density 1.717%

    No Known Activations