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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of penetration, both in a literal and metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atism
    -0.17
    _shapes
    -0.14
    quet
    -0.14
    ruba
    -0.14
    ibbon
    -0.14
     Comple
    -0.14
    ufe
    -0.14
    anse
    -0.14
     hva
    -0.14
    åł
    -0.13
    POSITIVE LOGITS
    depth
    0.24
     depth
    0.23
    -depth
    0.23
    deep
    0.23
     deep
    0.23
     depths
    0.23
     deepest
    0.21
     deeply
    0.20
     Depth
    0.20
     Deep
    0.19
    Act Density 0.143%

    No Known Activations