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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oons
    -0.17
    ĶåĽŀ
    -0.17
     hence
    -0.15
    863
    -0.15
    èĮĤ
    -0.14
    .scalablytyped
    -0.14
     toughness
    -0.14
    asted
    -0.14
    279
    -0.14
    iances
    -0.13
    POSITIVE LOGITS
    abyrin
    0.17
    ect
    0.16
    ória
    0.16
    spots
    0.16
    ness
    0.16
    bed
    0.15
    opoly
    0.15
    cha
    0.14
    toy
    0.14
    words
    0.14
    Act Density 0.017%

    No Known Activations