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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting characters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wand
    -0.15
    usher
    -0.15
    izedName
    -0.15
    ระ
    -0.14
    ospace
    -0.14
    stone
    -0.14
    obile
    -0.13
    ekler
    -0.13
    fa
    -0.13
    antic
    -0.13
    POSITIVE LOGITS
    \grid
    0.16
    iya
    0.15
    443
    0.15
    005
    0.15
    iag
    0.14
    181
    0.14
    ocz
    0.14
    ixin
    0.14
    æ¹¾
    0.14
    356
    0.14
    Act Density 0.009%

    No Known Activations