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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "Still."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricks
    -0.15
    usto
    -0.15
    baugh
    -0.14
    aurus
    -0.14
    ROL
    -0.14
    ĤŃ
    -0.14
    elles
    -0.14
    swire
    -0.14
    ola
    -0.13
    rtle
    -0.13
    POSITIVE LOGITS
    çĦ¶
    0.20
    birth
    0.19
    born
    0.19
    ness
    0.17
    onth
    0.17
     Evel
    0.16
    ennon
    0.15
    utow
    0.15
    SCI
    0.15
     waters
    0.15
    Act Density 0.017%

    No Known Activations