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

    Neuronpedia

    INDEX
    Explanations

    expressions of celebration and well-wishing sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zsche
    -0.15
    oring
    -0.15
    ifiable
    -0.15
    ered
    -0.15
    pg
    -0.15
    jerne
    -0.14
    gne
    -0.13
    à¹Ģà¸ĭ
    -0.13
    naire
    -0.13
    è§
    -0.13
    POSITIVE LOGITS
     trails
    0.29
     bel
    0.25
     Trails
    0.24
     endings
    0.20
    bel
    0.19
     Hour
    0.18
     almost
    0.18
     Bel
    0.17
     Almost
    0.17
     hour
    0.17
    Act Density 0.008%

    No Known Activations