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

    Neuronpedia

    INDEX
    Explanations

    significant verbs and terms indicating quality or status in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.15
    enders
    -0.14
     record
    -0.14
    _MODIFIED
    -0.14
    ieties
    -0.14
    227
    -0.13
    ufen
    -0.13
    xdb
    -0.13
    UNK
    -0.13
     Cal
    -0.13
    POSITIVE LOGITS
    'gc
    0.17
     Comparison
    0.15
    ouis
    0.15
     Compare
    0.15
     comparison
    0.15
    compare
    0.15
    .compare
    0.14
    comparison
    0.14
    arten
    0.14
     comparisons
    0.14
    Act Density 0.001%

    No Known Activations