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

    Neuronpedia

    INDEX
    Explanations

    expressions related to farewells and endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oeff
    -0.16
    ãĥªãĤ«
    -0.16
    noch
    -0.16
    à¥Ģप
    -0.15
     mess
    -0.15
    igli
    -0.14
    ViewState
    -0.14
     ven
    -0.14
    asti
    -0.14
     Mason
    -0.14
    POSITIVE LOGITS
     leaving
    0.17
    gger
    0.16
     permanently
    0.16
    wand
    0.15
    bud
    0.15
     tomorrow
    0.14
    elerik
    0.14
     permanent
    0.14
    bij
    0.14
    ê°Ī
    0.14
    Act Density 0.081%

    No Known Activations