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

    Neuronpedia

    INDEX
    Explanations

    the presence of noun forms and other specific upward or downward indications across a range of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.28
    plier
    -0.27
    ember
    -0.24
    aurant
    -0.23
    Ø©
    -0.22
    thing
    -0.21
    folio
    -0.21
    uary
    -0.20
    thesis
    -0.20
    acity
    -0.20
    POSITIVE LOGITS
     Wolff
    0.16
    ungs
    0.16
    ÅŁt
    0.15
    uards
    0.15
    ards
    0.14
    bbb
    0.14
    bras
    0.14
    places
    0.14
    íļĮìĿĺ
    0.14
    ej
    0.14
    Act Density 0.290%

    No Known Activations