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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML table code

    np_acts-logits-general · gemini-2.0-flash

    archaic spellings and formal words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.84
     a
    -0.84
     to
    -0.84
     de
    -0.83
     di
    -0.81
     an
    -0.81
     me
    -0.81
     sa
    -0.80
     car
    -0.80
     van
    -0.79
    POSITIVE LOGITS
     itſelf
    1.35
     myſelf
    1.24
     Cæsar
    1.19
     poffible
    1.18
     Monfieur
    1.15
     ſeveral
    1.10
     Houſe
    1.08
     pleaſure
    1.08
    <td>
    1.07
     themſelves
    1.06
    Act Density 0.019%

    No Known Activations