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

    Neuronpedia

    INDEX
    Explanations

    references to signals and their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corintios
    -0.80
    expandindo
    -0.73
     sorte
    -0.71
    CompilerServices
    -0.71
    Sparta
    -0.70
     BoxFit
    -0.70
     splen
    -0.69
     animés
    -0.68
     mesmos
    -0.68
     oublier
    -0.68
    POSITIVE LOGITS
     signals
    1.97
     Signal
    1.92
     signal
    1.91
     Signals
    1.87
    signals
    1.87
     SIGNAL
    1.74
    signal
    1.72
    Signal
    1.68
    Signals
    1.61
    SIGNAL
    1.61
    Act Density 0.067%

    No Known Activations