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

    Neuronpedia

    INDEX
    Explanations

    references to ISBN numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plier
    -0.17
    gow
    -0.16
    oop
    -0.15
    ven
    -0.14
    units
    -0.14
    uf
    -0.14
     RW
    -0.14
    á»ģ
    -0.13
    eto
    -0.13
    PerPage
    -0.13
    POSITIVE LOGITS
    978
    0.24
    977
    0.16
    979
    0.16
    981
    0.15
     Uns
    0.15
     мÑıг
    0.15
    971
    0.15
    958
    0.15
    hma
    0.14
    .soft
    0.14
    Act Density 0.006%

    No Known Activations