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

    Neuronpedia

    INDEX
    Explanations

    equality comparisons in code expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.75
    es
    -0.73
    ’
    -0.66
    [`
    -0.60
    y
    -0.60
    </u>
    -0.59
    er
    -0.58
    en
    -0.57
    '
    -0.56
    e
    -0.55
    POSITIVE LOGITS
     ==
    1.66
    ]==
    1.37
    ")==
    1.35
    ']==
    1.31
     ===
    1.27
    )==
    1.26
    ()==
    1.21
    ==
    1.12
    odyear
    1.02
     !=
    1.02
    Act Density 0.081%

    No Known Activations