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

    Neuronpedia

    INDEX
    Explanations

    references to the term "zero" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :],
    -0.67
    tigas
    -0.62
    ":["
    -0.62
     obligé
    -0.60
    ukone
    -0.60
     '../
    -0.60
    بل
    -0.59
    ://"
    -0.58
    iedler
    -0.58
     connexes
    -0.57
    POSITIVE LOGITS
     zero
    1.38
     Zero
    1.37
     ZERO
    1.37
    zero
    1.35
    Zero
    1.32
    ZERO
    1.27
     zeros
    1.24
     cero
    1.20
    zeros
    1.18
    Zeros
    1.16
    Act Density 0.066%

    No Known Activations