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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    offs
    -0.16
    eer
    -0.16
    offee
    -0.15
    MBER
    -0.15
    ics
    -0.15
    ovnÃŃ
    -0.14
    lac
    -0.14
    ilton
    -0.14
     모ëijIJ
    -0.14
    jem
    -0.14
    POSITIVE LOGITS
    igator
    0.28
     sorts
    0.27
    iance
    0.26
     kinds
    0.25
    ergy
    0.24
    usion
    0.24
    uring
    0.24
    owing
    0.24
    uded
    0.24
    ison
    0.23
    Act Density 0.198%

    No Known Activations