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

    Neuronpedia

    INDEX
    Explanations

    elements related to writing and documentation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ldr
    -0.17
     irr
    -0.16
    abr
    -0.16
    okens
    -0.15
    itters
    -0.14
    isque
    -0.14
    tega
    -0.14
    oro
    -0.14
     tut
    -0.14
    ogn
    -0.14
    POSITIVE LOGITS
     slips
    0.29
     paper
    0.28
     pad
    0.25
     ruled
    0.25
     papel
    0.24
     blank
    0.24
     pads
    0.23
     spiral
    0.22
     slip
    0.22
     index
    0.22
    Act Density 0.149%

    No Known Activations