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

    Neuronpedia

    INDEX
    Explanations

    technical terms and metrics related to performance analysis and resource evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olla
    -0.15
    PRINTF
    -0.15
    etto
    -0.15
     Dirt
    -0.15
    ellij
    -0.14
    cko
    -0.14
    dden
    -0.14
    plib
    -0.14
    ãģ¡
    -0.14
     disproportion
    -0.14
    POSITIVE LOGITS
     wee
    0.16
    渡
    0.15
    ropa
    0.14
    exels
    0.14
     Roth
    0.14
    èĩ´
    0.14
     bu
    0.13
     Tune
    0.13
    eling
    0.13
     Hag
    0.13
    Act Density 0.250%

    No Known Activations