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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical disabilities or accessibility features

    oai_token-act-pair · gpt-3.5-turbo

    references to disability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.90
    uin
    -0.90
    ablishment
    -0.87
    akeru
    -0.80
    apest
    -0.78
    alg
    -0.75
    andum
    -0.74
    orial
    -0.73
     Elections
    -0.73
    hens
    -0.72
    POSITIVE LOGITS
    locked
    0.78
    own
    0.77
    river
    0.74
     horm
    0.72
    locking
    0.72
     bay
    0.69
     disabled
    0.68
    utsche
    0.68
     aback
    0.67
    iron
    0.63
    Act Density 0.035%

    No Known Activations