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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating direction or mechanics of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.15
    @Module
    -0.15
    ocz
    -0.14
    adients
    -0.14
    .getAs
    -0.14
    atik
    -0.14
    _CLI
    -0.14
     LIMIT
    -0.14
    ÄįÃŃ
    -0.14
    ado
    -0.13
    POSITIVE LOGITS
    æ
    0.16
    cil
    0.15
     Tyler
    0.14
    ivalent
    0.14
     FT
    0.14
    sea
    0.14
    ivalence
    0.14
    æŃ©
    0.13
    letcher
    0.13
    fg
    0.13
    Act Density 0.004%

    No Known Activations