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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or processes involving change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     se
    -0.17
    lington
    -0.16
    allery
    -0.15
    rike
    -0.14
    ilib
    -0.14
    gress
    -0.14
    ongyang
    -0.14
    ombo
    -0.14
    panies
    -0.14
    ron
    -0.14
    POSITIVE LOGITS
     udál
    0.17
    zu
    0.15
     rest
    0.14
     addCriterion
    0.14
    chia
    0.14
    'n
    0.14
     Camb
    0.14
    ogg
    0.14
     herb
    0.13
    947
    0.13
    Act Density 0.026%

    No Known Activations