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

    Neuronpedia

    INDEX
    Explanations

    adjectives pertaining to rational thought or behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rationality and civility in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aunted
    -0.84
    ammy
    -0.79
    stals
    -0.78
    pain
    -0.77
    stress
    -0.75
     Strongh
    -0.75
    chu
    -0.73
    zona
    -0.71
    asso
    -0.71
    bender
    -0.71
    POSITIVE LOGITS
    tarian
    1.04
     enough
    0.80
    \\\\\\\\
    0.79
     minded
    0.78
     centrist
    0.78
     democracies
    0.77
    Reviewer
    0.77
     establishment
    0.76
    ynes
    0.75
    glers
    0.74
    Act Density 0.074%

    No Known Activations