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

    Neuronpedia

    INDEX
    Explanations

    words related to structure, organization, or categorization within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endale
    -0.17
    ekim
    -0.15
    heim
    -0.15
    aeper
    -0.15
    ernetes
    -0.14
     Rosen
    -0.14
    eyse
    -0.14
    izzo
    -0.14
    uentes
    -0.14
    icient
    -0.14
    POSITIVE LOGITS
    ight
    0.25
    ake
    0.25
    ay
    0.23
    ow
    0.23
    ock
    0.23
    ub
    0.23
    ar
    0.21
    uck
    0.21
    ate
    0.21
    ort
    0.21
    Act Density 0.603%

    No Known Activations