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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical versions or file structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neither
    -0.40
     Neither
    -0.32
    Neither
    -0.29
     III
    -0.22
     Triple
    -0.18
     nor
    -0.17
     Fourth
    -0.17
    ä¸ī个
    -0.16
     Three
    -0.16
    âĤĢ
    -0.15
    POSITIVE LOGITS
    2
    0.44
    Û²
    0.29
    ï¼Ĵ
    0.26
    २
    0.26
    Ù¢
    0.21
    äºĮ
    0.21
     اÙĦثاÙĨÙĬ
    0.21
     zwe
    0.21
    two
    0.19
     δÏįο
    0.19
    Act Density 0.058%

    No Known Activations