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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to geometric shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppe
    -0.18
    ssel
    -0.15
    otland
    -0.15
     ~=
    -0.15
    ccione
    -0.14
    ÑĸÑĢ
    -0.14
    agento
    -0.14
    çµ
    -0.14
     unlock
    -0.14
    Į¨
    -0.14
    POSITIVE LOGITS
     Bulgarian
    0.23
     Bulgaria
    0.20
     Sofia
    0.19
     имÑĥ
    0.17
    /bg
    0.16
    ove
    0.15
    inar
    0.15
     Console
    0.14
     Dimit
    0.14
     пеÑĩ
    0.14
    Act Density 0.005%

    No Known Activations