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

    Neuronpedia

    INDEX
    Explanations

    words related to negative emotions like shame and remorse

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shame and remorse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Trend
    -0.85
    tailed
    -0.77
    tails
    -0.76
    yip
    -0.72
    anto
    -0.66
    tail
    -0.63
    risome
    -0.63
    papers
    -0.62
    stakes
    -0.61
    ties
    -0.61
    POSITIVE LOGITS
     ashamed
    0.97
    xual
    0.95
     blush
    0.82
     cheeks
    0.76
     remorse
    0.75
    nikov
    0.71
    iates
    0.68
    leeve
    0.67
    ript
    0.67
    perture
    0.67
    Act Density 0.022%

    No Known Activations