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

    Neuronpedia

    INDEX
    Explanations

    mentions of negative events or actions, such as arrest, crime, or conflict

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADRA
    -0.70
     Shutterstock
    -0.70
     Wiz
    -0.68
     Archdemon
    -0.68
    EMENT
    -0.67
    VERTISEMENT
    -0.66
     Remastered
    -0.65
     Lanka
    -0.64
    ITION
    -0.64
     Cah
    -0.64
    POSITIVE LOGITS
    scale
    1.33
    bodied
    1.28
    sized
    1.27
    batch
    1.05
    size
    1.05
    circ
    1.05
    enough
    1.02
    unit
    1.01
    lived
    1.00
    level
    1.00
    Act Density 0.042%

    No Known Activations