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

    Neuronpedia

    INDEX
    Explanations

    tokens that represent variables or parameters in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     investi
    -0.78
     compri
    -0.74
     enthusi
    -0.74
     مرئيه
    -0.73
     expli
    -0.73
     esper
    -0.71
     equili
    -0.70
     iconFacebook
    -0.70
     exces
    -0.70
     opis
    -0.69
    POSITIVE LOGITS
    A
    1.31
    a
    1.24
    getA
    1.15
     A
    1.10
    aA
    1.05
     a
    0.96
    aData
    0.91
    bA
    0.90
     brancas
    0.87
     ansatte
    0.84
    Act Density 0.336%

    No Known Activations