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

    Neuronpedia

    INDEX
    Explanations

    instances of negation and expressions relating to uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    m
    -0.17
     Forecast
    -0.15
    isha
    -0.15
     Magn
    -0.15
    ary
    -0.15
    z
    -0.15
    stamp
    -0.15
     dow
    -0.15
     Shields
    -0.15
     stamp
    -0.15
    POSITIVE LOGITS
    INGTON
    0.17
    .Hit
    0.16
    getVar
    0.15
    lington
    0.15
    emento
    0.15
    GenerationStrategy
    0.15
    ccoli
    0.14
    *)_
    0.14
    .metamodel
    0.14
    Ãłn
    0.14
    Act Density 0.001%

    No Known Activations