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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pees
    -0.14
     witness
    -0.14
    elles
    -0.14
     dynamically
    -0.14
    ungan
    -0.14
    ÙħØ´
    -0.13
    ollapsed
    -0.13
    опиÑģ
    -0.13
    .dense
    -0.13
    elihood
    -0.13
    POSITIVE LOGITS
     distance
    0.20
     distances
    0.19
     Distance
    0.17
    distance
    0.15
    Distance
    0.15
     amount
    0.15
    /add
    0.15
    .cum
    0.15
    cum
    0.15
    nia
    0.15
    Act Density 0.130%

    No Known Activations