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

    Neuronpedia

    INDEX
    Explanations

    punctuations and symbols often associated with lists or bullet points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orph
    -0.15
    /sn
    -0.14
     sm
    -0.14
     Spor
    -0.14
    .weixin
    -0.14
    Äħd
    -0.14
     Salah
    -0.13
    év
    -0.13
     Potter
    -0.13
    sworth
    -0.13
    POSITIVE LOGITS
    è¾
    0.17
    æŁ³
    0.15
    inha
    0.15
    út
    0.14
    LinkId
    0.14
    üre
    0.14
    OptionPane
    0.14
     luáºŃn
    0.14
    uto
    0.14
    stery
    0.14
    Act Density 0.031%

    No Known Activations