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

    Neuronpedia

    INDEX
    Explanations

    references to lists or catalogs and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eree
    -0.18
     pain
    -0.17
    pai
    -0.16
     Pain
    -0.16
    realDonaldTrump
    -0.15
    457
    -0.15
    ppe
    -0.15
     Peanut
    -0.15
    499
    -0.15
    erin
    -0.15
    POSITIVE LOGITS
    èı¯
    0.17
    obar
    0.17
    =explode
    0.17
    éĬ
    0.17
    ãĥ¥
    0.16
    tura
    0.15
    åĵ¡
    0.14
    ãĥ§
    0.14
    _ctl
    0.14
     Bomb
    0.14
    Act Density 0.047%

    No Known Activations