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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of structured information or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    516
    -0.16
     vign
    -0.15
    amik
    -0.15
    eto
    -0.13
     SUMMARY
    -0.13
    anın
    -0.13
     Parr
    -0.13
    ottie
    -0.13
    ]={↵
    -0.13
     QPainter
    -0.13
    POSITIVE LOGITS
    ivery
    0.18
    .gameserver
    0.17
    urence
    0.15
    itty
    0.15
    ¶Į
    0.15
    ahren
    0.14
    reeze
    0.14
     below
    0.14
    _atomic
    0.14
    ØŃداث
    0.13
    Act Density 0.078%

    No Known Activations