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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate numerical statistics, values, or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nová
    -0.15
    OID
    -0.15
    ÎŃν
    -0.15
    §è¡Į
    -0.14
    ÅĻez
    -0.14
    odash
    -0.14
     migrationBuilder
    -0.14
    ibar
    -0.14
    ropa
    -0.13
    áš
    -0.13
    POSITIVE LOGITS
     half
    0.43
     HALF
    0.38
    half
    0.33
     Half
    0.33
    Half
    0.31
     two
    0.30
     Fully
    0.29
     fully
    0.29
    _half
    0.29
    fully
    0.27
    Act Density 0.096%

    No Known Activations