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

    Neuronpedia

    INDEX
    Explanations

    interrogative and conditional sentences or phrases that express uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     may
    -0.80
     is
    -0.79
     will
    -0.78
     can
    -0.73
     might
    -0.67
     could
    -0.66
     has
    -0.65
     was
    -0.64
     would
    -0.62
    glGen
    -0.62
    POSITIVE LOGITS
    Has
    1.83
     Has
    1.79
     Was
    1.71
    Was
    1.68
    Does
    1.66
     Does
    1.62
    Is
    1.60
    Will
    1.59
    Can
    1.57
     Is
    1.56
    Act Density 0.173%

    No Known Activations