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

    Neuronpedia

    INDEX
    Explanations

    technical terms and codes

    oai_token-act-pair · gpt-3.5-turbo

    references to languages or language-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.84
    uador
    -0.70
    ITNESS
    -0.68
     NAME
    -0.59
     Document
    -0.58
    pmwiki
    -0.58
    ÃįÃį
    -0.57
    UGC
    -0.57
    ãĥ¯ãĥ³
    -0.57
     GOODMAN
    -0.57
    POSITIVE LOGITS
     glide
    0.66
    Lago
    0.66
    pell
    0.65
     Igor
    0.63
    dfx
    0.62
     endif
    0.62
    lace
    0.62
     fold
    0.60
     Malk
    0.59
     lash
    0.59
    Act Density 0.890%

    No Known Activations