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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the concept of exclusivity or significance in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    137
    -0.15
    rai
    -0.14
    ades
    -0.14
    ãģĭãĤĬ
    -0.14
     Hoff
    -0.14
     Garn
    -0.14
    coins
    -0.14
    uglify
    -0.14
    ault
    -0.13
    yn
    -0.13
    POSITIVE LOGITS
    EDA
    0.16
    iswa
    0.16
    ols
    0.16
    velt
    0.14
    ãĥ©ãĥ³ãĥī
    0.14
    hower
    0.14
     váºŃy
    0.13
    vap
    0.13
    ä¹İ
    0.13
    ñas
    0.13
    Act Density 0.020%

    No Known Activations