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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparisons and different categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AREST
    -0.17
    ħį
    -0.17
    bjerg
    -0.16
    ograd
    -0.16
    еÑĢин
    -0.16
    ENTE
    -0.15
    inson
    -0.15
    ylan
    -0.15
    íĹĪ
    -0.14
    rary
    -0.14
    POSITIVE LOGITS
     lived
    0.15
    urga
    0.15
     th
    0.15
    itou
    0.14
    -ing
    0.14
     Caesar
    0.14
    owy
    0.14
     Frank
    0.14
     onOptionsItemSelected
    0.14
    SHA
    0.14
    Act Density 0.038%

    No Known Activations