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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating changes in quantity or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ¬
    -0.14
     Bilim
    -0.14
    lse
    -0.14
     None
    -0.14
    Ñģли
    -0.14
    achs
    -0.14
    igne
    -0.14
     Rosenstein
    -0.13
    -none
    -0.13
    ITTE
    -0.13
    POSITIVE LOGITS
     almost
    0.26
     leaps
    0.25
     factors
    0.24
     nearly
    0.23
     factor
    0.21
     double
    0.19
     more
    0.18
     tw
    0.18
    almost
    0.18
     Factors
    0.17
    Act Density 0.046%

    No Known Activations