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

    Neuronpedia

    INDEX
    Explanations

    mentions of firmware versions and related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Wynn
    -0.75
    jago
    -0.72
    Wallis
    -0.71
     Beale
    -0.69
    AccessFile
    -0.69
     Spector
    -0.68
    Ralf
    -0.68
     Wallis
    -0.67
    akei
    -0.66
     Caf
    -0.65
    POSITIVE LOGITS
     firmware
    1.36
    firmware
    1.29
     Firmware
    1.20
    Firmware
    1.19
    fw
    1.12
    FW
    1.03
     fw
    1.00
     FW
    0.94
    Datuak
    0.81
    modelName
    0.73
    Act Density 0.003%

    No Known Activations