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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize degree or intensity, particularly those using "so" and "much."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Farrell
    -0.17
    inis
    -0.16
    isha
    -0.15
    usic
    -0.15
    ingu
    -0.15
    mast
    -0.14
    arel
    -0.14
     Lazy
    -0.14
    ASTER
    -0.14
    hazi
    -0.14
    POSITIVE LOGITS
     much
    0.18
    Å¡Å¥
    0.17
     anymore
    0.17
    vertisement
    0.17
    ãĥ³ãĥĸ
    0.16
     Much
    0.15
    -called
    0.15
    much
    0.15
    .dsl
    0.15
     defaultCenter
    0.15
    Act Density 0.025%

    No Known Activations