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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ament
    -0.19
    hra
    -0.16
    ray
    -0.16
    hu
    -0.16
    angular
    -0.15
    enger
    -0.15
    arel
    -0.15
    itude
    -0.15
    zcze
    -0.15
    lar
    -0.15
    POSITIVE LOGITS
    xFFFFFFFF
    0.27
    xffff
    0.25
    xFFFF
    0.25
    xffffffff
    0.24
    ï¸ı
    0.22
    xFF
    0.21
    xffffff
    0.20
    xff
    0.19
    xDE
    0.19
    xFFFFFF
    0.17
    Act Density 0.170%

    No Known Activations