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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    p
    -0.27
    c
    -0.26
    e
    -0.24
    d
    -0.24
    b
    -0.21
    s
    -0.21
    l
    -0.20
    m
    -0.19
    t
    -0.19
    f
    -0.19
    POSITIVE LOGITS
    /o
    0.16
     průbÄĽhu
    0.15
    addock
    0.15
    tc
    0.15
    gn
    0.15
    kr
    0.15
    ï¸ı
    0.14
    toi
    0.14
    esco
    0.14
    acobian
    0.14
    Act Density 0.559%

    No Known Activations