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

    Neuronpedia

    INDEX
    Explanations

    references to periods of time (e.g., years, months)

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Case
    -0.67
    Mech
    -0.67
    Pri
    -0.67
    Fac
    -0.67
    ORD
    -0.64
    ice
    -0.63
     Cosponsors
    -0.62
    Console
    -0.62
    cause
    -0.61
    wealth
    -0.61
    POSITIVE LOGITS
     hiatus
    0.98
    ynthesis
    0.87
    dding
    0.82
     slog
    0.79
     reckoning
    0.75
     exhausting
    0.73
    cation
    0.70
     absence
    0.69
     stint
    0.69
     apiece
    0.68
    Act Density 0.079%

    No Known Activations