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

    Neuronpedia

    INDEX
    Explanations

    references to symbols and representations related to shapes or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .gg
    -0.17
     nominal
    -0.16
    ariat
    -0.16
    arel
    -0.15
    stones
    -0.14
    ummer
    -0.14
    uctose
    -0.14
    avors
    -0.14
    dition
    -0.13
    elves
    -0.13
    POSITIVE LOGITS
     shape
    0.20
     shaped
    0.17
     shapes
    0.17
    shape
    0.17
     formations
    0.16
     outline
    0.16
    forma
    0.16
     Shape
    0.16
    Shape
    0.15
    _tpl
    0.15
    Act Density 0.148%

    No Known Activations