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

    Neuronpedia

    INDEX
    Explanations

    adverbs and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elles
    -0.17
    azzi
    -0.15
    ollo
    -0.14
    antine
    -0.14
    алÑĮ
    -0.14
    loff
    -0.14
    (æ°´
    -0.14
    kad
    -0.14
    odesk
    -0.14
    ideo
    -0.13
    POSITIVE LOGITS
    nn
    0.28
    tics
    0.22
    eder
    0.21
    rics
    0.21
    wood
    0.21
    mph
    0.19
    eda
    0.19
    olly
    0.18
    nnen
    0.18
    nda
    0.18
    Act Density 0.038%

    No Known Activations