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

    Neuronpedia

    INDEX
    Explanations

    inequality comparisons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    7
    -0.73
     Moos
    -0.68
     trúc
    -0.63
    空的
    -0.62
    atud
    -0.60
     katal
    -0.59
     Ere
    -0.58
    timo
    -0.58
     kép
    -0.58
     Villar
    -0.57
    POSITIVE LOGITS
     !=
    2.17
    !=
    1.74
    ()!=
    1.49
    ]!=
    1.49
    )!=
    1.41
     !==
    1.28
    !=-
    1.15
    !='
    1.12
    !="
    0.96
    ]!='
    0.95
    Act Density 0.039%

    No Known Activations