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

    Neuronpedia

    INDEX
    Explanations

    references to codes or identifiers in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    hline
    -0.76
    )|^{
    -0.70
     hyp
    -0.66
     Genn
    -0.66
    ิลปะ
    -0.66
     LCCN
    -0.65
     Holmes
    -0.64
    -0.64
     kies
    -0.63
    apis
    -0.63
    POSITIVE LOGITS
    xc
    1.34
     xc
    1.27
     XC
    1.02
    XC
    0.97
     Pard
    0.87
    BibitemShut
    0.82
     deleteAll
    0.82
    RemoveField
    0.81
     contextLoads
    0.79
    envolvimento
    0.77
    Act Density 0.008%

    No Known Activations