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

    Neuronpedia

    INDEX
    Explanations

    affirmations and enthusiastic punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atica
    -0.16
     Goldberg
    -0.16
    ulia
    -0.15
     memcmp
    -0.15
     unpredict
    -0.14
    ophy
    -0.14
    Ñıн
    -0.14
    /Common
    -0.13
    asia
    -0.13
     Cloth
    -0.13
    POSITIVE LOGITS
     Place
    0.28
    Place
    0.26
     place
    0.26
     Heat
    0.23
     PLACE
    0.23
     Directions
    0.22
    Directions
    0.22
     Diss
    0.21
    Heat
    0.21
     mix
    0.21
    Act Density 0.086%

    No Known Activations