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

    Neuronpedia

    INDEX
    Explanations

    references to angels, their grace, and metaphoric comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lately
    -0.18
     soon
    -0.16
    ique
    -0.15
    絶
    -0.15
     recently
    -0.15
     each
    -0.14
     sometimes
    -0.14
     confuse
    -0.14
    784
    -0.14
    ìĶ©
    -0.14
    POSITIVE LOGITS
     originally
    0.22
     Originally
    0.20
    Originally
    0.17
     Was
    0.17
    æĽ¾
    0.16
    \Mapping
    0.15
    /original
    0.15
    Was
    0.15
     бÑĭла
    0.15
    hatt
    0.14
    Act Density 0.018%

    No Known Activations