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

    Neuronpedia

    INDEX
    Explanations

    terms related to records and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λÏī
    -0.15
    utow
    -0.15
     Rat
    -0.15
    _RW
    -0.15
    iquid
    -0.14
    êu
    -0.14
    rape
    -0.14
    Compat
    -0.14
    abras
    -0.13
    isper
    -0.13
    POSITIVE LOGITS
    -breaking
    0.20
    breaking
    0.17
     amount
    0.17
     sÆ°
    0.17
    amount
    0.17
     number
    0.16
    ptrdiff
    0.16
    number
    0.16
    -level
    0.16
    edly
    0.16
    Act Density 0.023%

    No Known Activations