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

    Neuronpedia

    INDEX
    Explanations

    references to forms of oligarchy and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zin
    -0.17
    scal
    -0.16
    zure
    -0.16
    ogi
    -0.14
    oji
    -0.14
    inou
    -0.13
    shops
    -0.13
    stellen
    -0.13
    stalk
    -0.13
    arak
    -0.13
    POSITIVE LOGITS
    exampleInput
    0.19
    ulet
    0.17
     Dude
    0.16
    ìį¨
    0.16
    reater
    0.15
    iah
    0.15
    ãĥ³ãĥī
    0.15
    olec
    0.15
    ud
    0.14
    utherford
    0.14
    Act Density 0.002%

    No Known Activations