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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to measurement, shapes, and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velope
    -0.18
    agger
    -0.18
     envelope
    -0.17
    itemap
    -0.17
     robe
    -0.16
     blouse
    -0.16
    erah
    -0.16
     heap
    -0.15
    ajan
    -0.15
     bouquet
    -0.15
    POSITIVE LOGITS
     screens
    0.29
     frames
    0.28
     boards
    0.26
     caps
    0.25
     pens
    0.25
     boxes
    0.24
     tops
    0.23
     flags
    0.22
     covers
    0.22
     handles
    0.22
    Act Density 1.080%

    No Known Activations