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

    Neuronpedia

    INDEX
    Explanations

    references to personal identifiers and privacy-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iera
    -0.16
    scribe
    -0.15
     Hab
    -0.15
    izioni
    -0.15
    elf
    -0.15
    icc
    -0.14
     se
    -0.14
    rips
    -0.14
    wich
    -0.14
     Measure
    -0.14
    POSITIVE LOGITS
    aggio
    0.16
    aux
    0.15
    ayout
    0.14
    essler
    0.14
    achat
    0.14
    ãĥ©ãĤ¯
    0.13
     integ
    0.13
    bette
    0.13
    aÄĩ
    0.13
    éĻ·
    0.13
    Act Density 0.007%

    No Known Activations