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

    Neuronpedia

    INDEX
    Explanations

    statistical representations of proportions and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lap
    -0.14
     UIBar
    -0.14
    ibase
    -0.14
    alfa
    -0.14
    SAFE
    -0.14
    urm
    -0.14
    eldorf
    -0.14
    733
    -0.14
    bach
    -0.13
    umbed
    -0.13
    POSITIVE LOGITS
     of
    0.21
     Shields
    0.16
     delle
    0.15
    /all
    0.14
     ÏĦÏīν
    0.14
    unma
    0.14
    gili
    0.14
    oles
    0.14
     Cup
    0.14
    aux
    0.13
    Act Density 0.042%

    No Known Activations