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

    Neuronpedia

    INDEX
    Explanations

    words related to reparations or negative actions imposed on individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of reparations or related concepts of accountability and restitution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.94
    ERY
    -0.81
     Abyss
    -0.75
    ggle
    -0.73
     Ducks
    -0.72
     Cage
    -0.70
     Bruins
    -0.69
    GER
    -0.67
     GER
    -0.65
     tuberculosis
    -0.65
    POSITIVE LOGITS
    utations
    1.46
    ublic
    1.24
    ulsive
    1.19
    roach
    1.14
    rieve
    1.14
    uted
    1.13
    rehensible
    1.13
    rint
    1.13
    orters
    1.11
    utation
    1.11
    Act Density 0.018%

    No Known Activations