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

    Neuronpedia

    INDEX
    Explanations

    specific words indicating geographical locations or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iest
    -0.18
    steen
    -0.15
    ium
    -0.15
    onom
    -0.15
     nov
    -0.15
    aring
    -0.14
    dbe
    -0.14
    ui
    -0.14
    ards
    -0.14
     shove
    -0.14
    POSITIVE LOGITS
    /gtest
    0.18
    .lift
    0.15
    /tags
    0.14
    kil
    0.14
    chio
    0.14
    łģ
    0.14
    mary
    0.14
    вен
    0.14
    YPES
    0.14
    ammu
    0.13
    Act Density 0.019%

    No Known Activations