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

    Neuronpedia

    INDEX
    Explanations

    film titles or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourd
    -0.17
    ¼åIJĪ
    -0.15
    ι
    -0.15
    ouz
    -0.14
    nees
    -0.14
    esser
    -0.14
    strate
    -0.14
    allback
    -0.14
    oslav
    -0.14
    é¢Ħè§Ī
    -0.14
    POSITIVE LOGITS
    ë¦Ħ
    0.14
     å¯
    0.14
    exp
    0.14
     Hep
    0.13
    _overlay
    0.13
    iterr
    0.13
    &action
    0.13
     Gregory
    0.13
    _sensitive
    0.13
    eler
    0.13
    Act Density 0.034%

    No Known Activations