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

    Neuronpedia

    INDEX
    Explanations

    expressions of dependency or reliance on systems, people, or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.18
    itez
    -0.17
    /Dk
    -0.15
    lement
    -0.15
    izontally
    -0.15
    itom
    -0.15
    orp
    -0.15
    AXB
    -0.15
    arefa
    -0.15
    chalk
    -0.14
    POSITIVE LOGITS
     upon
    0.35
     heav
    0.30
     Upon
    0.29
    Upon
    0.29
     heavy
    0.28
     heavier
    0.28
     heavily
    0.28
    upon
    0.27
     Heavy
    0.24
    Heavy
    0.23
    Act Density 0.017%

    No Known Activations