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

    Neuronpedia

    INDEX
    Explanations

    terms related to neurons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ToBounds
    -0.63
    żdż
    -0.63
    CppMethod
    -0.61
    Royce
    -0.57
    helle
    -0.57
    ^-
    -0.56
     مرئيه
    -0.56
     Hel
    -0.55
    ToRemove
    -0.55
    }^{-\
    -0.55
    POSITIVE LOGITS
     neurons
    1.23
    neurons
    1.11
    urons
    1.10
    neuron
    1.05
     Neuron
    1.02
     neuron
    0.98
     Hike
    0.85
    Neuron
    0.85
     SPIE
    0.77
     MacGregor
    0.77
    Act Density 0.005%

    No Known Activations