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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that suggest duality, contrast, or specific identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sunrise
    -0.15
    atoon
    -0.15
    IGO
    -0.14
     Canter
    -0.14
    кÑĤÑĥ
    -0.14
    ãĥ¼ãĥij
    -0.13
    bote
    -0.13
    utherford
    -0.13
    occasion
    -0.13
    .quick
    -0.13
    POSITIVE LOGITS
    ewan
    0.16
    æľ¬
    0.15
    edu
    0.15
    quina
    0.15
    hin
    0.15
    SG
    0.14
    uka
    0.14
    608
    0.14
    cluded
    0.14
    ixin
    0.14
    Act Density 0.017%

    No Known Activations