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

    Neuronpedia

    INDEX
    Explanations

    terms related to destructive events and their aftermath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kul
    -0.17
     istem
    -0.15
    stras
    -0.15
    VT
    -0.14
    ainer
    -0.14
    typeid
    -0.14
     addCriterion
    -0.14
     Dynam
    -0.13
    iten
    -0.13
    <const
    -0.13
    POSITIVE LOGITS
    ofil
    0.16
     tum
    0.16
    ÑģÑĮого
    0.15
    807
    0.14
    uga
    0.14
     err
    0.14
    ipeg
    0.14
    ót
    0.14
    ạch
    0.13
    uto
    0.13
    Act Density 0.087%

    No Known Activations