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

    Neuronpedia

    INDEX
    Explanations

    references to physical forms and shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.21
    ioso
    -0.17
    jas
    -0.17
    ucc
    -0.17
    éĹ´
    -0.16
    iaz
    -0.15
    eday
    -0.15
    land
    -0.15
    day
    -0.15
    ati
    -0.15
    POSITIVE LOGITS
    peare
    0.25
    (shape
    0.23
     Shape
    0.23
    less
    0.21
     shaped
    0.21
     shape
    0.21
    lessness
    0.20
    shape
    0.19
    /Form
    0.19
    fully
    0.19
    Act Density 0.013%

    No Known Activations