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

    Neuronpedia

    INDEX
    Explanations

    terms related to effort and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -Col
    -0.17
    -a
    -0.16
    -Sh
    -0.16
    -On
    -0.16
    -A
    -0.15
    -INF
    -0.14
    âĢĮÙħ
    -0.14
     Forgotten
    -0.14
    -b
    -0.14
    eyed
    -0.14
    POSITIVE LOGITS
     -
    0.16
    epam
    0.16
    çī§
    0.15
    -wise
    0.14
    çĴ
    0.14
    -looking
    0.14
    ëŀĢ
    0.14
    ec
    0.14
    utral
    0.13
    erve
    0.13
    Act Density 0.098%

    No Known Activations