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

    Neuronpedia

    INDEX
    Explanations

    terms related to actions or events being carried out

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of activity or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocard
    -0.81
    Boss
    -0.76
    gling
    -0.73
    oiler
    -0.71
     passage
    -0.68
    inka
    -0.67
    skinned
    -0.64
    haul
    -0.64
    ophe
    -0.63
    ulously
    -0.63
    POSITIVE LOGITS
     undertaken
    0.99
    ional
    0.94
    ivism
    0.88
     activities
    0.87
     activity
    0.86
     patterns
    0.83
    iveness
    0.81
     verbs
    0.81
    uated
    0.79
    ives
    0.79
    Act Density 0.034%

    No Known Activations