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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.88
     Theſe
    -0.80
     Shaksp
    -0.78
     blest
    -0.78
     lidl
    -0.73
     creeds
    -0.70
     operands
    -0.69
     Aleppo
    -0.69
     Mahomet
    -0.69
     Pallas
    -0.69
    POSITIVE LOGITS
    --)
    0.73
    ()]
    0.71
     =>
    0.70
    +");
    0.69
    ={
    0.69
    +')
    0.67
     (
    0.64
    ());
    0.63
    >({
    0.63
    )),
    0.63
    Act Density 0.313%

    No Known Activations