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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kas
    -0.16
    iesz
    -0.15
     å¹
    -0.14
    _HOOK
    -0.14
    agus
    -0.14
    asse
    -0.14
     Eisen
    -0.14
     باز
    -0.14
    ListNode
    -0.13
    andest
    -0.13
    POSITIVE LOGITS
     ways
    0.15
    .cloudflare
    0.15
    Це
    0.15
    "class
    0.14
    bjerg
    0.14
    LEN
    0.14
    neys
    0.13
    ambi
    0.13
     Ways
    0.13
    hist
    0.13
    Act Density 0.150%

    No Known Activations