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

    Neuronpedia

    INDEX
    Explanations

    terms related to requests or inquiries directed at individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     altogether
    -0.17
    pper
    -0.16
     rất
    -0.15
     somewhere
    -0.15
    skins
    -0.15
    arer
    -0.15
     entirety
    -0.15
    ively
    -0.15
    izen
    -0.14
    çļĦæĺ¯
    -0.14
    POSITIVE LOGITS
    /e
    0.30
     else
    0.28
     remotely
    0.23
    THING
    0.21
     whatsoever
    0.21
    -any
    0.20
     anytime
    0.20
     anybody
    0.20
     anywhere
    0.20
    _else
    0.20
    Act Density 0.059%

    No Known Activations