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

    Neuronpedia

    INDEX
    Explanations

    the presence of proper nouns and titles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.16
    ombo
    -0.16
    modifiable
    -0.15
    umbo
    -0.14
    wards
    -0.14
    653
    -0.14
    ensis
    -0.14
    iron
    -0.13
    dy
    -0.13
     freeze
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĢ
    0.18
    ugi
    0.16
    æ¸Ī
    0.15
    ubl
    0.14
    icion
    0.14
    iline
    0.14
    lerde
    0.14
    &eacute
    0.13
    ewan
    0.13
    igen
    0.13
    Act Density 0.707%

    No Known Activations