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

    Neuronpedia

    INDEX
    Explanations

    IC-related codes

    oai_token-act-pair · gpt-3.5-turbo

    references to the International Consortium of Investigative Journalists (ICIJ)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itism
    -0.78
    wich
    -0.75
    hood
    -0.67
    hip
    -0.67
    ments
    -0.66
    tenance
    -0.66
    spread
    -0.66
    wards
    -0.65
    selves
    -0.65
    zee
    -0.64
    POSITIVE LOGITS
    ANN
    1.28
    IJ
    1.01
    trl
    1.00
    ustom
    0.99
    BM
    0.93
    ategory
    0.93
    ritical
    0.92
    ULAR
    0.92
    ross
    0.89
    REAM
    0.89
    Act Density 0.036%

    No Known Activations