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

    Neuronpedia

    INDEX
    Explanations

    phrases related to analysis or conclusions based on evidence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic concerns and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Warranty
    -0.77
    ãĤ´ãĥ³
    -0.73
     spared
    -0.67
     Worth
    -0.65
    ulously
    -0.64
     Answers
    -0.64
     Fare
    -0.63
    Synopsis
    -0.63
     Slay
    -0.63
     Tanaka
    -0.62
    POSITIVE LOGITS
     behavi
    0.98
     disproportion
    0.98
     anecd
    0.97
    entimes
    0.96
     [
    0.95
     exacerbate
    0.93
     perception
    0.91
     secondly
    0.91
     systemic
    0.90
     exacerbated
    0.88
    Act Density 0.741%

    No Known Activations