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

    Neuronpedia

    INDEX
    Explanations

    references to music, films, and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chron
    -0.20
     aud
    -0.19
     grav
    -0.18
     parent
    -0.18
     craft
    -0.18
     gender
    -0.18
     birth
    -0.17
     smart
    -0.17
     dish
    -0.17
     equal
    -0.17
    POSITIVE LOGITS
     Murder
    0.26
     Poison
    0.26
     Ghost
    0.26
     Midnight
    0.26
     Dead
    0.26
     Broken
    0.25
     Lonely
    0.24
     Kiss
    0.24
     Dirty
    0.24
     Night
    0.24
    Act Density 0.128%

    No Known Activations