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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and author-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ary
    -0.19
    elyn
    -0.16
    oyo
    -0.16
    bral
    -0.16
    ayers
    -0.16
    emens
    -0.15
    yor
    -0.15
    ãģ°
    -0.15
    weg
    -0.15
    edd
    -0.14
    POSITIVE LOGITS
    ship
    0.36
    itative
    0.35
    itarian
    0.30
    izations
    0.27
    ing
    0.26
    izes
    0.24
    ised
    0.24
    itat
    0.23
    ial
    0.23
    SHIP
    0.22
    Act Density 0.030%

    No Known Activations