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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "swing" and variations of the word "rotate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cejas
    -0.55
     lecciones
    -0.52
     Asamblea
    -0.52
     tatouage
    -0.50
     determinación
    -0.50
     actualidad
    -0.50
     chaleco
    -0.49
     asamblea
    -0.49
     Producción
    -0.49
     destrucción
    -0.49
    POSITIVE LOGITS
     rot
    1.07
     Rot
    0.97
    Rot
    0.90
     ROT
    0.79
    rot
    0.79
     rots
    0.65
    Rotten
    0.65
     rotten
    0.63
     Rotten
    0.62
     rotting
    0.56
    Act Density 0.301%

    No Known Activations