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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical movements and positioning

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprehen
    -0.63
     vainly
    -0.62
     Whence
    -0.57
     nobly
    -0.55
     gaily
    -0.55
     indescri
    -0.53
     unspeak
    -0.53
     tolerably
    -0.53
     ineffec
    -0.52
    sgn
    -0.51
    POSITIVE LOGITS
     own
    0.73
     reputa
    0.57
     brille
    0.57
     vinci
    0.55
    cluse
    0.54
     bunda
    0.53
     ché
    0.53
     bebes
    0.52
     dè
    0.52
     hamburg
    0.52
    Act Density 0.228%

    No Known Activations