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

    Neuronpedia

    INDEX
    Explanations

    terms related to urging action or emphasizing importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express strong sentiments or opinions about specific elements or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.83
    ÃĥÃĤ
    -0.80
    senal
    -0.75
     subur
    -0.73
    oÄŁ
    -0.72
    Course
    -0.70
    Tu
    -0.70
    çīĪ
    -0.70
    FP
    -0.69
    bart
    -0.69
    POSITIVE LOGITS
     redeem
    0.77
     lesson
    0.76
     tribute
    0.74
     formula
    0.73
     takeaway
    0.71
     distinguishing
    0.69
     prophecy
    0.69
     defining
    0.69
     irony
    0.68
     consistency
    0.68
    Act Density 0.165%

    No Known Activations