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

    Neuronpedia

    INDEX
    Explanations

    words related to glacial and icy environments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ethnicity and racial categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.69
    debian
    -0.68
    uden
    -0.65
    UG
    -0.65
    zig
    -0.65
    rb
    -0.64
     Recomm
    -0.63
    rug
    -0.63
     Lexington
    -0.61
     Later
    -0.61
    POSITIVE LOGITS
    acial
    1.26
    anguage
    0.87
    vertisements
    0.79
     gestures
    0.78
    gemony
    0.76
    gments
    0.75
     feats
    0.75
     citiz
    0.75
     slurs
    0.73
    opian
    0.73
    Act Density 0.009%

    No Known Activations