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

    Neuronpedia

    INDEX
    Explanations

    references to degradation or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.17
    åĿĬ
    -0.17
    eries
    -0.15
    ÂŃi
    -0.14
    ynth
    -0.14
     volta
    -0.14
    asString
    -0.14
     readline
    -0.14
    uga
    -0.13
    èĪ
    -0.13
    POSITIVE LOGITS
    itch
    0.15
     Hoff
    0.15
    095
    0.15
    ÏĦÏī
    0.14
     Bearing
    0.14
    _fold
    0.14
    _firestore
    0.14
     selfie
    0.14
    olynomial
    0.13
    ñana
    0.13
    Act Density 0.042%

    No Known Activations