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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '{@
    -0.57
    язы
    -0.57
     nadie
    -0.55
    yet
    -0.54
    uxley
    -0.54
    ̈́
    -0.53
     CreateTagHelper
    -0.53
     صوتيه
    -0.52
     termino
    -0.51
     THOUGH
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.72
    Hentet
    0.66
     thụ
    0.65
    Geplaatst
    0.62
     esterni
    0.61
     برانيه
    0.56
    tură
    0.56
    umina
    0.56
    Abitanti
    0.55
    makeText
    0.55
    Act Density 0.056%

    No Known Activations