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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    emotions related to negative sentiments and frustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.74
    icle
    -0.73
    ramer
    -0.69
     actu
    -0.67
     antioxid
    -0.67
     nut
    -0.65
     destruct
    -0.63
     pist
    -0.63
     compos
    -0.62
     handy
    -0.62
    POSITIVE LOGITS
    fulness
    0.96
    lessness
    0.88
    ishment
    0.80
    FUL
    0.78
    fully
    0.78
    hurst
    0.77
    uously
    0.77
    ously
    0.76
    worthiness
    0.75
    wart
    0.75
    Act Density 0.108%

    No Known Activations