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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions related to variables and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    p
    -0.32
    c
    -0.31
    e
    -0.29
    d
    -0.25
    s
    -0.24
    r
    -0.24
    b
    -0.23
    t
    -0.23
    l
    -0.23
    f
    -0.22
    POSITIVE LOGITS
    /o
    0.18
    unifu
    0.16
    addock
    0.15
    illion
    0.15
    ndl
    0.15
    gn
    0.15
    pras
    0.14
    sez
    0.14
    chandle
    0.13
    seo
    0.13
    Act Density 0.548%

    No Known Activations