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

    Neuronpedia

    INDEX
    Explanations

    words related to reparation or repair

    oai_token-act-pair · gpt-3.5-turbo

    references to reparations or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.89
     Abyss
    -0.83
    ERY
    -0.81
     Cage
    -0.81
     Bruins
    -0.79
     Ducks
    -0.76
     Leap
    -0.72
    ppo
    -0.72
     Galile
    -0.69
     Tale
    -0.66
    POSITIVE LOGITS
    utations
    1.51
    rint
    1.15
    uted
    1.14
    ublic
    1.13
    onse
    1.12
    utation
    1.11
    osition
    1.11
    lying
    1.11
    ainted
    1.09
    arations
    1.09
    Act Density 0.012%

    No Known Activations