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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and variables related to statistical or probabilistic models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unkt
    -0.15
    ioc
    -0.14
     Dot
    -0.14
    -dot
    -0.14
     Square
    -0.14
    éĻ£
    -0.14
     square
    -0.14
     dot
    -0.14
    ix
    -0.13
    ACES
    -0.13
    POSITIVE LOGITS
    ÏĢ
    0.23
     mes
    0.22
    pi
    0.21
    decay
    0.20
     charm
    0.20
    charged
    0.20
     pi
    0.20
    charm
    0.20
    γη
    0.20
    γγ
    0.20
    Act Density 0.008%

    No Known Activations