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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation related to probabilities and statistical distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    d
    -0.28
    n
    -0.26
    t
    -0.25
    k
    -0.24
    x
    -0.23
    y
    -0.23
    m
    -0.23
    s
    -0.23
    g
    -0.22
    ly
    -0.21
    POSITIVE LOGITS
     _
    0.27
     t
    0.27
     a
    0.27
     m
    0.26
     v
    0.25
     n
    0.25
     g
    0.25
     L
    0.25
     S
    0.25
     T
    0.25
    Act Density 0.153%

    No Known Activations