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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Hare" and its variations within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hare, harriers, hares

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.54
     surla
    -0.47
    :✨
    -0.46
    حوالہ
    -0.43
    McC
    -0.43
     revés
    -0.43
     Embaj
    -0.41
    __*/
    -0.40
    guém
    -0.40
    Christoph
    -0.39
    POSITIVE LOGITS
     Hare
    2.55
    Hare
    2.48
     hare
    2.14
    hare
    2.08
    hares
    1.23
     harem
    1.05
     Hara
    0.70
    hared
    0.68
    hair
    0.68
     Haver
    0.63
    Act Density 0.004%

    No Known Activations