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

    Neuronpedia

    INDEX
    Explanations

    acronyms containing the letters 'IC' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the International Consortium of Investigative Journalists (ICIJ) and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.84
    tenance
    -0.71
    selves
    -0.70
    wards
    -0.69
     Nanto
    -0.68
    ï¸
    -0.68
    ged
    -0.67
    geons
    -0.66
    ãĥĦ
    -0.65
    witz
    -0.65
    POSITIVE LOGITS
    ANN
    1.16
    trl
    0.98
    entric
    0.97
    ustom
    0.93
    IJ
    0.92
    ENSE
    0.92
    onduct
    0.91
    ategory
    0.87
    ritical
    0.87
    helle
    0.87
    Act Density 0.036%

    No Known Activations