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

    Neuronpedia

    INDEX
    Explanations

    expressions of friendliness and positive interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.90
    onOptions
    -0.88
    <h5>
    -0.79
     onPostExecute
    -0.78
     NSCoder
    -0.75
    protoimpl
    -0.73
    subplots
    -0.70
    ínsula
    -0.69
     maș
    -0.69
    InSection
    -0.68
    POSITIVE LOGITS
     friendly
    1.48
     Friendly
    1.38
    Friendly
    1.32
    friendly
    1.27
     friendliness
    1.12
     unfriendly
    1.04
     Pleasant
    0.98
    Pleasant
    0.97
     pleasant
    0.94
     vriende
    0.94
    Act Density 0.071%

    No Known Activations