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

    Neuronpedia

    INDEX
    Explanations

    short acronyms or initials followed by a numerical value like "H9" or "F10"

    oai_token-act-pair · gpt-3.5-turbo

    letters or abbreviations that represent media organizations or networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.85
    itals
    -0.81
    uphem
    -0.75
    ptin
    -0.73
    rawdownloadcloneembedreportprint
    -0.71
    shaw
    -0.71
    itri
    -0.67
    ãĥĥãĥī
    -0.67
    ãĤ©
    -0.64
    uga
    -0.64
    POSITIVE LOGITS
    OPS
    0.96
    USH
    0.84
    AMY
    0.84
    GS
    0.82
    OP
    0.81
    IDA
    0.80
    ZE
    0.80
    ZI
    0.80
    TP
    0.77
    KA
    0.76
    Act Density 0.107%

    No Known Activations