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

    Neuronpedia

    INDEX
    Explanations

    terms related to current states, conditions, and trends

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.79
    alties
    -0.75
    amn
    -0.73
    ppings
    -0.73
    amins
    -0.69
    aths
    -0.68
    later
    -0.68
    wright
    -0.67
    kick
    -0.66
    amy
    -0.63
    POSITIVE LOGITS
     incarnation
    1.09
     iteration
    0.87
     developments
    0.86
     whereabouts
    0.84
     predicament
    0.79
     spate
    0.77
     edition
    0.76
     trends
    0.75
     situation
    0.74
     fashionable
    0.73
    Act Density 1.109%

    No Known Activations