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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Link" within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.81
     actionGroup
    -0.78
    ãĥ£
    -0.77
     proble
    -0.70
    Þ
    -0.70
    rely
    -0.68
    âķIJâķIJ
    -0.67
     conflic
    -0.65
    pering
    -0.65
    ccording
    -0.64
    POSITIVE LOGITS
    edin
    1.42
    later
    1.14
    witz
    1.09
    ering
    0.94
    ed
    0.90
    backer
    0.86
    ioned
    0.85
    ibrary
    0.84
    hammer
    0.80
    er
    0.80
    Act Density 0.015%

    No Known Activations