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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to floating-point numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hner
    -0.49
     parts
    -0.46
     moeite
    -0.43
     every
    -0.42
    語り
    -0.41
    ی
    -0.41
     Kinds
    -0.41
    SharedDtor
    -0.40
     înd
    -0.39
     Ender
    -0.38
    POSITIVE LOGITS
     float
    1.84
     Float
    1.79
    float
    1.71
     FLOAT
    1.68
    Float
    1.66
     floats
    1.61
     floating
    1.41
     Floating
    1.40
    FLOAT
    1.39
     floated
    1.38
    Act Density 0.104%

    No Known Activations