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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technical specifications and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athers
    -0.21
    olic
    -0.20
    ioxide
    -0.18
    oux
    -0.17
    wart
    -0.15
    ±
    -0.15
    -pt
    -0.15
    igli
    -0.15
    326
    -0.14
    urning
    -0.14
    POSITIVE LOGITS
     Wh
    0.22
    ostel
    0.20
     wh
    0.19
    Wh
    0.18
     Maur
    0.18
    енÑģ
    0.16
    wh
    0.16
    OTE
    0.15
    onda
    0.15
    bst
    0.15
    Act Density 0.020%

    No Known Activations