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

    Neuronpedia

    INDEX
    Explanations

    words related to unfortunate or negative circumstances

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness or negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.76
    rouse
    -0.75
    eers
    -0.74
    amins
    -0.73
    afort
    -0.72
    insula
    -0.72
    eer
    -0.72
    arters
    -0.71
    rosse
    -0.71
    uese
    -0.71
    POSITIVE LOGITS
     sadly
    0.95
    ा
    0.90
     tragically
    0.80
    ãĤ´ãĥ³
    0.80
    à¥
    0.80
     unfortunately
    0.78
     Sadly
    0.77
    ÃĽ
    0.76
     regrett
    0.75
     parted
    0.74
    Act Density 0.013%

    No Known Activations