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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦÙĪد
    -0.15
    认
    -0.14
    uncture
    -0.14
    lore
    -0.14
    croft
    -0.14
    ÐĵÐŀ
    -0.14
    craft
    -0.14
    wa
    -0.13
     goose
    -0.13
    angan
    -0.13
    POSITIVE LOGITS
     Leban
    0.17
     Spicer
    0.16
    .setView
    0.14
     Lloyd
    0.14
     scn
    0.14
     Orc
    0.14
    .easy
    0.14
     Khu
    0.13
    PIP
    0.13
    zÅij
    0.13
    Act Density 0.019%

    No Known Activations