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

    Neuronpedia

    INDEX
    Explanations

    patterns related to high numerical values or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inia
    -0.17
    ulary
    -0.15
    emouth
    -0.14
    etto
    -0.14
     sez
    -0.14
    uter
    -0.13
    olem
    -0.13
    lla
    -0.13
     next
    -0.13
    controls
    -0.13
    POSITIVE LOGITS
    áte
    0.16
    /XMLSchema
    0.15
     Tie
    0.14
    cdecl
    0.14
     вÑģего
    0.14
     Aid
    0.14
    ivas
    0.14
    ë²
    0.14
    SetBranch
    0.14
    ê³
    0.13
    Act Density 0.044%

    No Known Activations