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

    Neuronpedia

    INDEX
    Explanations

    occurrences of brackets or quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    virt
    -0.16
     Virt
    -0.16
    chet
    -0.15
    inx
    -0.15
    REM
    -0.14
    ibil
    -0.14
    oldem
    -0.14
     æ
    -0.14
    eref
    -0.13
    sled
    -0.13
    POSITIVE LOGITS
    pector
    0.15
    _CHIP
    0.14
    akin
    0.13
    麼
    0.13
    magic
    0.13
    ye
    0.13
    ÙĪرÙĬØ©
    0.13
     Chip
    0.13
    ine
    0.13
     ;č↵
    0.13
    Act Density 0.013%

    No Known Activations