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

    Neuronpedia

    INDEX
    Explanations

    instances of the abbreviation "S."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffe
    -0.19
    erialize
    -0.17
    eum
    -0.16
    gnore
    -0.16
    ttp
    -0.15
    tml
    -0.15
    irtual
    -0.15
    TEGER
    -0.14
     continuity
    -0.14
    o
    -0.14
    POSITIVE LOGITS
    uper
    0.26
    ecure
    0.24
    ever
    0.24
    pecific
    0.23
    chool
    0.23
    quare
    0.23
    elf
    0.22
    upported
    0.22
    mart
    0.22
    ocial
    0.22
    Act Density 0.008%

    No Known Activations