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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.16
    instead
    -0.16
    ctic
    -0.15
    าะ
    -0.15
    formik
    -0.15
    ettle
    -0.15
    ysa
    -0.15
    avorite
    -0.15
    ÑĢап
    -0.14
    zers
    -0.14
    POSITIVE LOGITS
    cs
    0.17
    ipi
    0.16
    aison
    0.15
     exc
    0.15
     else
    0.15
    phans
    0.15
     Dixon
    0.15
    .call
    0.15
    icha
    0.14
    naments
    0.14
    Act Density 0.140%

    No Known Activations