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

    Neuronpedia

    INDEX
    Explanations

    specific terms and abbreviations related to performance metrics and categorization in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Briggs
    -0.15
    oras
    -0.15
    anca
    -0.15
     connected
    -0.15
    ued
    -0.15
    tere
    -0.14
    ÑĢоÑģÑĤо
    -0.14
    ãģĦãģĭ
    -0.14
    pron
    -0.13
    ebe
    -0.13
    POSITIVE LOGITS
    ipop
    0.15
    jom
    0.15
     bbw
    0.14
    zet
    0.14
    hem
    0.14
    llib
    0.14
    yar
    0.13
     Ulus
    0.13
    hom
    0.13
    ham
    0.13
    Act Density 0.011%

    No Known Activations