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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or prediction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future events or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.67
     endeavor
    -0.62
    plug
    -0.58
    era
    -0.58
    oriented
    -0.56
    achi
    -0.55
    irs
    -0.54
    zer
    -0.53
     didnt
    -0.52
     endeavour
    -0.52
    POSITIVE LOGITS
     plenty
    1.07
     ample
    0.86
     lots
    0.83
     no
    0.80
     some
    0.80
     exceptions
    0.79
     tons
    0.78
    ample
    0.77
     alot
    0.75
     fewer
    0.74
    Act Density 0.038%

    No Known Activations