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

    Neuronpedia

    INDEX
    Explanations

    references to global entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arra
    -0.17
    cken
    -0.17
    nice
    -0.15
    usa
    -0.15
    atcher
    -0.15
    ansi
    -0.15
     remorse
    -0.15
     Walters
    -0.14
    LEASE
    -0.14
    unda
    -0.14
    POSITIVE LOGITS
    Wide
    0.23
     Wide
    0.22
    -wide
    0.21
    wide
    0.21
     wide
    0.19
    (World
    0.18
    -ren
    0.17
    -class
    0.16
    oa
    0.15
    ήν
    0.14
    Act Density 0.033%

    No Known Activations