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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feelings of satisfaction or pride

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive feelings or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     distinguished
    -0.68
     favoured
    -0.66
     pioneered
    -0.64
    nis
    -0.62
     coveted
    -0.62
    inguished
    -0.62
     sought
    -0.61
    ewitness
    -0.60
    swick
    -0.59
    acles
    -0.58
    POSITIVE LOGITS
    stories
    0.83
    ãĤ´
    0.79
     lapt
    0.77
    ALLY
    0.73
    andi
    0.71
    enough
    0.70
    terday
    0.69
     vibrations
    0.65
     :)
    0.64
     è£ıè
    0.64
    Act Density 0.029%

    No Known Activations