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

    Neuronpedia

    INDEX
    Explanations

    frequent numerical values or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    horabuena
    -0.60
    ariConfig
    -0.52
     propOrder
    -0.52
     pescoço
    -0.51
     outono
    -0.51
    ConstraintMaker
    -0.50
    atott
    -0.49
     Rother
    -0.48
     Stump
    -0.48
    (&:
    -0.48
    POSITIVE LOGITS
    ⑦
    0.54
     surla
    0.53
    GIVEREF
    0.51
    UnusedPrivate
    0.51
    örgy
    0.50
    Filmographie
    0.49
    icel
    0.49
    มาะ
    0.48
    NewUrlParser
    0.48
     Julio
    0.47
    Act Density 0.416%

    No Known Activations