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

    Neuronpedia

    INDEX
    Explanations

    boolean values and their corresponding states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orc
    -0.16
    olik
    -0.15
     Dit
    -0.15
    enda
    -0.14
    ulo
    -0.14
    ra
    -0.14
    OTES
    -0.14
    éo
    -0.14
    land
    -0.14
    fab
    -0.14
    POSITIVE LOGITS
     oppon
    0.14
    umble
    0.14
    éļİ
    0.14
    andle
    0.14
    алом
    0.13
    IMA
    0.13
    hani
    0.13
     slov
    0.13
    ecn
    0.13
    ÑĴ
    0.13
    Act Density 0.025%

    No Known Activations