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

    Neuronpedia

    INDEX
    Explanations

    various types or categories of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ry
    -0.23
    aries
    -0.18
    ary
    -0.17
    lea
    -0.17
    iser
    -0.17
    ming
    -0.16
    rp
    -0.15
    ites
    -0.15
    mer
    -0.15
    rod
    -0.15
    POSITIVE LOGITS
    æħĭ
    0.21
    ahead
    0.17
    íĴĪ
    0.15
     latter
    0.15
    -prepend
    0.15
    etting
    0.15
    fully
    0.15
    kiye
    0.15
    asily
    0.15
    tingham
    0.15
    Act Density 0.139%

    No Known Activations