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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of drawing, such as drawings, drew, drawn, etc

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "draw" and its variations, indicating focus on comparisons or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «
    -0.73
    gram
    -0.72
     âĶľâĶĢâĶĢ
    -0.67
    ORPG
    -0.65
     Capitalism
    -0.62
    Unix
    -0.62
    âķIJâķIJ
    -0.62
    Giving
    -0.61
    acre
    -0.61
    ìĿ
    -0.60
    POSITIVE LOGITS
     parallels
    1.22
     attention
    1.17
     comparisons
    1.14
     inspiration
    1.08
     nearer
    0.99
     ire
    0.97
     upon
    0.97
     distinctions
    0.95
     conclusions
    0.93
     stares
    0.88
    Act Density 0.036%

    No Known Activations