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

    Neuronpedia

    INDEX
    Explanations

    various mathematical operations and numerical conversions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.64
    -
    -0.56
     dvou
    -0.49
     +
    -0.48
    +
    -0.48
     F
    -0.47
     two
    -0.46
    :
    -0.46
     three
    -0.46
     trzech
    -0.46
    POSITIVE LOGITS
     itſelf
    1.08
     myſelf
    1.03
     ſtate
    0.97
    ]")]
    0.96
     Jefus
    0.90
     purpoſe
    0.88
    IntoConstraints
    0.88
     faſt
    0.88
    DockStyle
    0.88
    ')")
    0.88
    Act Density 0.921%

    No Known Activations