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

    Neuronpedia

    INDEX
    Explanations

    references to programming language constructs or libraries

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     péné
    -0.79
    Còn
    -0.78
     poffe
    -0.76
    +-+-
    -0.76
     Kompon
    -0.75
    horabuena
    -0.73
     sprzedaż
    -0.72
    jface
    -0.71
     "%"
    -0.71
    edata
    -0.70
    POSITIVE LOGITS
     cl
    1.60
     CL
    1.59
     Cl
    1.53
    cl
    1.52
    CL
    1.38
    Cl
    1.29
     clon
    1.15
     Kl
    1.12
     Cly
    1.11
     McCl
    1.05
    Act Density 0.024%

    No Known Activations