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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation in a structured formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mojom
    -0.22
    #af
    -0.22
     --↵
    -0.20
    #ae
    -0.20
    #ga
    -0.19
    couz
    -0.19
     --
    -0.19
    @nate
    -0.18
    >NN
    -0.18
    taboola
    -0.18
    POSITIVE LOGITS
    0
    0.32
    x
    0.29
    u
    0.28
    y
    0.26
    U
    0.25
    z
    0.24
    X
    0.23
    Y
    0.23
    1
    0.23
    V
    0.22
    Act Density 0.263%

    No Known Activations