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

    Neuronpedia

    INDEX
    Explanations

    references to geographical divisions and transnational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ravel
    -0.17
    خراج
    -0.17
    Ñĩила
    -0.15
    ockets
    -0.15
    inerary
    -0.15
    indr
    -0.14
    DownList
    -0.14
    anchor
    -0.14
    åĿĢ
    -0.14
     corners
    -0.14
    POSITIVE LOGITS
     divide
    0.28
     pond
    0.27
     aisle
    0.26
     Pond
    0.25
     threshold
    0.25
    pond
    0.25
    divide
    0.22
     fence
    0.22
     barrier
    0.22
     bridge
    0.21
    Act Density 0.057%

    No Known Activations