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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or responses that are conditional or dependent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zw
    -0.17
    è±
    -0.14
    ZW
    -0.14
    aring
    -0.14
    fol
    -0.14
    zt
    -0.14
    -0.14
    amar
    -0.14
    anou
    -0.14
    prites
    -0.14
    POSITIVE LOGITS
     extremes
    0.28
     lengths
    0.27
     bed
    0.19
     sleep
    0.19
     task
    0.19
     trouble
    0.18
     places
    0.17
     lenght
    0.17
     movies
    0.17
     jail
    0.17
    Act Density 0.053%

    No Known Activations