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

    Neuronpedia

    INDEX
    Explanations

    words related to feelings of discomfort or negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bower
    -0.17
    /bower
    -0.17
    illac
    -0.17
    çŃĨ
    -0.16
    stor
    -0.16
    STYLE
    -0.16
    ATAR
    -0.15
    ulp
    -0.15
    firm
    -0.15
    ãĥ¡ãĥ³ãĥĪ
    -0.15
    POSITIVE LOGITS
    /on
    0.17
     w
    0.17
     VStack
    0.17
     Leading
    0.16
     Sanity
    0.16
    jet
    0.16
    ippi
    0.14
     pr
    0.14
     Jet
    0.14
     Shaw
    0.14
    Act Density 0.025%

    No Known Activations