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

    Neuronpedia

    INDEX
    Explanations

    actions related to pouring and covering in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovel
    -0.16
    825
    -0.14
     truy
    -0.14
    noho
    -0.14
    792
    -0.14
    usz
    -0.14
    utsch
    -0.13
    arel
    -0.13
    amba
    -0.13
    ÙĥاÙĦ
    -0.13
    POSITIVE LOGITS
     gasoline
    0.23
     mud
    0.20
     pitch
    0.20
     Formal
    0.20
     formal
    0.19
     paint
    0.19
     tar
    0.19
     semen
    0.19
     Dynam
    0.19
     dirt
    0.19
    Act Density 0.357%

    No Known Activations