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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusion, isolation, and avoidance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exclusion from social, political, or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.77
    yss
    -0.74
    raq
    -0.70
    acca
    -0.70
    ectar
    -0.66
    llular
    -0.65
    rien
    -0.64
    EY
    -0.63
     Herald
    -0.62
    attr
    -0.62
    POSITIVE LOGITS
     exclusion
    1.01
    ary
    0.92
    ism
    0.78
    lessness
    0.77
     spoilers
    0.76
     prejudice
    0.76
     screening
    0.75
    clusion
    0.74
    naire
    0.73
     bias
    0.72
    Act Density 0.010%

    No Known Activations