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

    Neuronpedia

    INDEX
    Explanations

    citations and referencing formats in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amp
    -0.20
    raquo
    -0.19
    nbsp
    -0.18
    mlin
    -0.16
    olik
    -0.15
    sted
    -0.14
    igidBody
    -0.14
     æ¼
    -0.14
    ãĥ³ãĥĹ
    -0.14
    ectl
    -0.13
    POSITIVE LOGITS
    []{
    0.28
    ìĶ
    0.17
    atori
    0.15
    []
    0.15
    Blend
    0.15
    idor
    0.14
    bÃŃ
    0.14
    инок
    0.14
     tela
    0.14
    []{↵
    0.14
    Act Density 0.007%

    No Known Activations