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

    Neuronpedia

    INDEX
    Explanations

    numerical values preceded by a specific symbol

    oai_token-act-pair · gpt-3.5-turbo

    numeric data related to votes and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prises
    -0.82
    arte
    -0.76
    liga
    -0.74
    nesday
    -0.72
    hran
    -0.71
    prise
    -0.69
    enance
    -0.69
    taining
    -0.65
    urred
    -0.65
    atoes
    -0.65
    POSITIVE LOGITS
    00
    1.07
    th
    0.84
    åĤ
    0.70
    TH
    0.68
    mm
    0.68
    MM
    0.66
    gow
    0.66
     Unic
    0.64
    01
    0.64
     deficient
    0.63
    Act Density 0.053%

    No Known Activations