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

    Neuronpedia

    INDEX
    Explanations

    references to tricks or deceptive techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SessionFactory
    -0.83
    
    -0.81
     Bleach
    -0.81
     Burrow
    -0.81
     crickets
    -0.78
     Bem
    -0.78
     Bourgoin
    -0.77
    MLLoader
    -0.77
    IContainer
    -0.75
     CRS
    -0.75
    POSITIVE LOGITS
     tricks
    1.43
     trick
    1.43
    trick
    1.32
    tricks
    1.29
     Trick
    1.17
     twist
    1.05
    Trick
    1.04
     truco
    0.99
    twist
    0.99
     twists
    0.98
    Act Density 0.092%

    No Known Activations