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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AppCompat
    -0.63
    nacht
    -0.62
    juvant
    -0.60
    PRESA
    -0.55
    habi
    -0.52
    0
    -0.52
     Bartol
    -0.52
    rauch
    -0.50
    2
    -0.50
    μπ
    -0.49
    POSITIVE LOGITS
    ']))
    0.91
    yntaxException
    0.84
     BIBSYS
    0.80
     kasarigan
    0.79
    بوابة
    0.77
    enumi
    0.77
    "}>
    0.75
    "])
    0.75
    lgari
    0.73
    IsInitialized
    0.72
    Act Density 0.094%

    No Known Activations