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

    Neuronpedia

    INDEX
    Explanations

    words related to unraveling or solving complex mysteries and narratives

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to the concept of unraveling or disclosing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.80
    auri
    -0.68
     pronoun
    -0.67
    urse
    -0.64
    ¥µ
    -0.64
    ãĥĨãĤ£
    -0.62
    dash
    -0.61
    Sham
    -0.60
    aurus
    -0.60
     Advocate
    -0.59
    POSITIVE LOGITS
    ing
    0.95
    pers
    0.86
    ed
    0.79
    eding
    0.78
    ritten
    0.78
     unravel
    0.77
    oing
    0.75
    sten
    0.74
    edIn
    0.74
     tarn
    0.72
    Act Density 0.019%

    No Known Activations