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

    Neuronpedia

    INDEX
    Explanations

    references to space-related events or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fila
    -0.19
    शà¤ķ
    -0.16
    Ú¯ÛĮر
    -0.15
     плен
    -0.15
    -bars
    -0.14
    alytics
    -0.14
     Pompe
    -0.14
    olta
    -0.14
    OOM
    -0.13
    rollers
    -0.13
    POSITIVE LOGITS
     Dragon
    0.31
     Falcon
    0.30
     Star
    0.28
     Hawth
    0.27
     Crew
    0.27
     Grass
    0.26
    Dragon
    0.26
     dragon
    0.25
     Dragons
    0.24
    Star
    0.23
    Act Density 0.010%

    No Known Activations