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

    Neuronpedia

    INDEX
    Explanations

    specific entities and their roles or interactions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sobie
    -0.16
    aks
    -0.16
    arin
    -0.15
     нами
    -0.15
    engin
    -0.15
     нÑĮого
    -0.14
     Ñģобой
    -0.14
    them
    -0.14
     ihm
    -0.14
     siendo
    -0.14
    POSITIVE LOGITS
     a
    0.33
     an
    0.29
     another
    0.27
     some
    0.26
     something
    0.23
     the
    0.22
     everything
    0.22
     permission
    0.21
     access
    0.21
    /us
    0.20
    Act Density 0.166%

    No Known Activations