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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation or gratitude towards others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and thankfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.74
    xtap
    -0.66
     depending
    -0.64
    depending
    -0.60
    oiler
    -0.59
     blaming
    -0.58
     defaults
    -0.58
    ocide
    -0.58
    ģ«
    -0.57
     losers
    -0.57
    POSITIVE LOGITS
     courage
    0.79
     tirelessly
    0.78
     responsibly
    0.75
    !]
    0.75
     brave
    0.74
     generously
    0.74
     :)
    0.73
     yesterday
    0.68
     courageous
    0.67
     peacefully
    0.67
    Act Density 0.181%

    No Known Activations