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

    Neuronpedia

    INDEX
    Explanations

    elements related to machine learning and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilos
    -0.15
    orbit
    -0.14
    apid
    -0.14
    PTS
    -0.14
    uras
    -0.14
    æıĽ
    -0.14
    ulong
    -0.14
     modulo
    -0.14
    hazi
    -0.14
    890
    -0.14
    POSITIVE LOGITS
     bias
    0.32
     biases
    0.28
    bias
    0.28
     Bias
    0.28
     dropout
    0.27
    Bias
    0.25
     Dropout
    0.25
     layer
    0.23
    _bias
    0.23
     Layer
    0.23
    Act Density 0.001%

    No Known Activations