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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction or dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of satisfaction or contentment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.87
     teasp
    -0.79
    ghai
    -0.71
    akin
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    ourage
    -0.69
    hops
    -0.65
    sites
    -0.65
    fighter
    -0.64
    ftime
    -0.64
    POSITIVE LOGITS
     regards
    1.19
    standing
    1.11
     regard
    1.00
     impunity
    0.93
     respect
    0.89
    stood
    0.86
     dignity
    0.80
    drawn
    0.78
    draw
    0.75
     what
    0.74
    Act Density 0.061%

    No Known Activations