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

    Neuronpedia

    INDEX
    Explanations

    explanations or statements within text

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements about predictions and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Specifically
    -0.75
    Suggest
    -0.74
    Analy
    -0.72
    Indeed
    -0.71
    DIT
    -0.71
    suggest
    -0.71
    Recommend
    -0.68
    phasis
    -0.68
     explan
    -0.67
    Materials
    -0.67
    POSITIVE LOGITS
     immortality
    1.09
     Elvis
    0.96
     Adolf
    0.93
    thood
    0.92
     afterlife
    0.89
     Kobe
    0.88
     Jesus
    0.88
     Oprah
    0.88
     Peyton
    0.87
     heaven
    0.87
    Act Density 0.587%

    No Known Activations