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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and variables in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToWorld
    -0.16
    unken
    -0.16
    neau
    -0.15
    adol
    -0.14
    SystemService
    -0.14
    nave
    -0.14
     otherwise
    -0.14
    çĴ
    -0.14
    PURE
    -0.14
    engers
    -0.14
    POSITIVE LOGITS
    rimp
    0.17
    anz
    0.17
    ãģ£ãģ±
    0.16
    itele
    0.15
    boa
    0.15
    etleri
    0.15
     Wein
    0.14
     Combo
    0.13
    Æ°á»
    0.13
    COPE
    0.13
    Act Density 0.205%

    No Known Activations