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

    Neuronpedia

    INDEX
    Explanations

    communication prompts and warnings related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erton
    -0.19
    elt
    -0.15
    cho
    -0.15
     superv
    -0.14
     bomb
    -0.14
    wand
    -0.14
    anas
    -0.14
     å±
    -0.14
    -expand
    -0.13
     RedirectToAction
    -0.13
    POSITIVE LOGITS
    zf
    0.14
     modal
    0.14
    ̣
    0.14
     Äijá»
    0.14
     Comm
    0.14
     Rough
    0.14
    gence
    0.14
     Modal
    0.13
    ence
    0.13
    ä¸ĭåİ»
    0.13
    Act Density 0.229%

    No Known Activations