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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and identifiers related to policies, research, and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upd
    -0.17
    asti
    -0.15
     cơm
    -0.15
    _reading
    -0.14
    agi
    -0.14
     Ná
    -0.14
     scrut
    -0.14
    jure
    -0.14
    421
    -0.14
    agnost
    -0.14
    POSITIVE LOGITS
     splash
    0.15
     rum
    0.15
    iones
    0.14
    ipar
    0.14
    adian
    0.14
    emap
    0.14
     carp
    0.14
    olog
    0.14
    kaar
    0.14
    ã
    0.14
    Act Density 0.004%

    No Known Activations