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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols often associated with mathematical or programming expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.67
    CppMethod
    -0.60
     autorytatywna
    -0.59
    dhury
    -0.58
    WithIOException
    -0.58
    ließlich
    -0.57
    sitivity
    -0.56
     ouverts
    -0.56
    titleMargin
    -0.53
     canlynol
    -0.53
    POSITIVE LOGITS
     tip
    0.53
    HomeAsUpEnabled
    0.52
    rsc
    0.50
    dera
    0.49
     BoxDecoration
    0.48
     King
    0.48
    nocache
    0.47
    uintptr
    0.47
     neither
    0.46
     Reg
    0.46
    Act Density 0.016%

    No Known Activations