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

    Neuronpedia

    INDEX
    Explanations

    terms related to distinct categories or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allowNull
    -0.48
    KommentareTeilen
    -0.47
    )_/¯
    -0.45
    뀜
    -0.44
    UnitTesting
    -0.42
    udsman
    -0.42
     Intelli
    -0.41
    arb
    -0.41
    weeney
    -0.40
    IsContent
    -0.40
    POSITIVE LOGITS
     different
    1.28
    different
    1.27
     differently
    1.24
    Different
    1.21
     Different
    1.18
     DIFFERENT
    1.09
     distinto
    1.04
     differ
    1.01
     differs
    1.01
     diferente
    1.00
    Act Density 0.496%

    No Known Activations