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

    Neuronpedia

    INDEX
    Explanations

    references to news reporting and media coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kate
    -0.15
    anus
    -0.14
    äl
    -0.14
    criptor
    -0.14
    stricted
    -0.13
     tack
    -0.13
    ãĥ¼ãĥŃ
    -0.13
    ayan
    -0.13
    awi
    -0.13
    ãĥĨãĥ«
    -0.13
    POSITIVE LOGITS
     KH
    0.29
     station
    0.29
     WT
    0.28
     Channel
    0.28
     WC
    0.28
     KG
    0.27
     stations
    0.27
     WR
    0.27
     WB
    0.27
     WL
    0.27
    Act Density 0.174%

    No Known Activations