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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordion
    -0.14
    zon
    -0.14
    orris
    -0.14
    анÑĤи
    -0.14
    iple
    -0.14
    abase
    -0.13
    orth
    -0.13
    WN
    -0.13
     ëijĺ
    -0.13
    amarin
    -0.13
    POSITIVE LOGITS
     non
    0.28
     ones
    0.20
    mixed
    0.20
    non
    0.19
     mixed
    0.19
     Non
    0.19
     semi
    0.19
     others
    0.19
     NON
    0.18
    others
    0.17
    Act Density 0.431%

    No Known Activations