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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize inclusivity and universality of experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to collective or inclusive terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wrath
    -0.67
    veyard
    -0.67
    iger
    -0.67
    word
    -0.64
    tnc
    -0.63
    odan
    -0.63
    eln
    -0.63
     testament
    -0.62
     Horses
    -0.61
     Resurrection
    -0.61
    POSITIVE LOGITS
     else
    1.91
     Else
    1.30
    else
    1.21
     except
    1.08
     involved
    1.07
    Else
    1.06
     imaginable
    1.00
     who
    0.95
    THING
    0.87
     conceivable
    0.85
    Act Density 0.060%

    No Known Activations