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

    Neuronpedia

    INDEX
    Explanations

    a specific foreign language or code pattern

    oai_token-act-pair · gpt-3.5-turbo

    sequences of certain characters or symbols, possibly indicating a specific encoding or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.56
    cia
    -0.53
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.52
    iqueness
    -0.49
    âĸ¬
    -0.49
     Fargo
    -0.48
     Nad
    -0.48
     Yor
    -0.48
     Cassidy
    -0.48
    @#&
    -0.47
    POSITIVE LOGITS
    charg
    0.63
    usercontent
    0.57
    adders
    0.57
     broom
    0.54
    steam
    0.53
    izont
    0.52
    umblr
    0.52
    site
    0.51
    ousel
    0.51
    route
    0.50
    Act Density 0.783%

    No Known Activations