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

    Neuronpedia

    INDEX
    Explanations

    references to health and safety concerns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.16
    andes
    -0.15
     Spears
    -0.14
    ieg
    -0.14
    imes
    -0.14
    igua
    -0.14
    ot
    -0.14
    ếp
    -0.14
    igel
    -0.14
    237
    -0.13
    POSITIVE LOGITS
     unborn
    0.16
    ycastle
    0.15
    uard
    0.15
    ventus
    0.15
    ystack
    0.15
     innocent
    0.15
    ije
    0.14
    à¤Ĥà¤ļ
    0.14
     delicate
    0.14
     cush
    0.14
    Act Density 0.066%

    No Known Activations