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

    Neuronpedia

    INDEX
    Explanations

    words related to significant actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avana
    -0.16
    alytics
    -0.16
    uyo
    -0.15
    ÅĤo
    -0.15
     nackte
    -0.14
    makt
    -0.14
     mechanism
    -0.14
    eg
    -0.13
    PropertyChanged
    -0.13
     Cove
    -0.13
    POSITIVE LOGITS
    etin
    0.16
    ì»
    0.15
    .uni
    0.15
    ilde
    0.14
    532
    0.14
     Redemption
    0.14
    _PICTURE
    0.14
    aze
    0.14
    _UD
    0.14
    witch
    0.13
    Act Density 0.002%

    No Known Activations