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

    Neuronpedia

    INDEX
    Explanations

    article sections in a text

    oai_token-act-pair · gpt-3.5-turbo

    sections that indicate a continuation of an article or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     squared
    -0.70
    ãĥı
    -0.70
    imm
    -0.68
     appar
    -0.65
    liber
    -0.64
    eg
    -0.64
    pher
    -0.63
    urus
    -0.63
    NAS
    -0.60
     Roh
    -0.60
    POSITIVE LOGITS
     Thumbnails
    1.13
     Below
    1.07
    allery
    0.85
    icter
    0.81
    querque
    0.78
    jriwal
    0.77
     veter
    0.76
    ileaks
    0.75
    achev
    0.75
    oday
    0.74
    Act Density 0.004%

    No Known Activations