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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "author" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ίÏīν
    -0.17
    -eyed
    -0.15
    ary
    -0.15
    eyes
    -0.15
    chant
    -0.15
    berra
    -0.15
    legates
    -0.15
    elyn
    -0.15
    756
    -0.14
    符
    -0.14
    POSITIVE LOGITS
    itative
    0.27
    itarian
    0.23
    ship
    0.22
    ised
    0.18
    entic
    0.18
    ing
    0.17
    иÑĤеÑĤ
    0.16
    icity
    0.16
    itive
    0.15
    izes
    0.15
    Act Density 0.031%

    No Known Activations