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

    Neuronpedia

    INDEX
    Explanations

    mentions of constraints or limitations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agina
    -0.15
    γκα
    -0.14
    ÏĦια
    -0.14
    uo
    -0.14
    imat
    -0.14
    duk
    -0.14
    ¯
    -0.13
    ych
    -0.13
    winter
    -0.13
    /lo
    -0.13
    POSITIVE LOGITS
     confines
    0.27
     bounds
    0.25
     boundaries
    0.21
     scope
    0.21
    scope
    0.20
     reach
    0.20
     mere
    0.19
     borders
    0.19
    .Strict
    0.19
     ë²Ķ
    0.17
    Act Density 0.065%

    No Known Activations