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

    Neuronpedia

    INDEX
    Explanations

    references to gates in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indol
    -0.54
    SharedCtor
    -0.53
    iibo
    -0.52
    Cout
    -0.51
     incr
    -0.50
     jojo
    -0.50
     sceptre
    -0.50
     Jojo
    -0.49
     Aquarius
    -0.49
     infarction
    -0.48
    POSITIVE LOGITS
     gate
    0.57
     Gate
    0.52
     temprano
    0.50
     serpiente
    0.50
     bezpośred
    0.48
     späteren
    0.46
    0.46
     específicamente
    0.46
     föres
    0.46
     temprana
    0.46
    Act Density 0.211%

    No Known Activations