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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the objectives or goals of a study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withstanding
    -0.78
    eper
    -0.76
    ciaż
    -0.72
    ______
    -0.70
    ———
    -0.70
    sillon
    -0.68
    UDC
    -0.66
    buc
    -0.66
     McDonnell
    -0.66
    ▬▬▬▬
    -0.65
    POSITIVE LOGITS
     Ains
    0.96
     Heim
    0.83
     Kain
    0.81
     DMG
    0.80
    存于互联网档案馆
    0.80
    UrlResolution
    0.79
     Lain
    0.78
     Cain
    0.76
    brains
    0.75
    astricht
    0.74
    Act Density 0.059%

    No Known Activations