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

    Neuronpedia

    INDEX
    Explanations

    words associated with temperature or popularity, specifically the term "hot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    sut
    -0.16
    jee
    -0.15
    ously
    -0.15
    arian
    -0.15
    ately
    -0.15
    磨
    -0.14
    hood
    -0.14
    atchet
    -0.14
    Ùħ
    -0.14
    POSITIVE LOGITS
    -hot
    0.23
    spots
    0.18
    elper
    0.18
    -blood
    0.17
    endar
    0.16
     hotter
    0.15
    imir
    0.15
    ly
    0.15
    /fire
    0.15
    äºİ
    0.14
    Act Density 0.019%

    No Known Activations