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

    Neuronpedia

    INDEX
    Explanations

    instances of high-frequency terms or constructs in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     برانيه
    -0.59
     <<<<<<<<<<<<<<
    -0.55
    <&
    -0.55
     &&
    -0.53
    autoconfigure
    -0.51
    زی
    -0.51
    额
    -0.51
    額
    -0.50
     probably
    -0.49
    RefNanny
    -0.49
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.78
    Portály
    0.75
     maîtres
    0.75
    InjectAttribute
    0.75
    ↵↵↵↵
    0.70
    ↵↵↵
    0.70
     intermédiaire
    0.70
     projective
    0.69
     popoli
    0.67
    ↵↵↵↵↵↵↵
    0.67
    Act Density 0.069%

    No Known Activations