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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors indicating relationships between ideas or components

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

    Follows conjunctions "and" or "but"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -0.96
     Efq
    -0.87
     ſame
    -0.86
     faſt
    -0.86
     purpoſe
    -0.85
     iſt
    -0.84
    neſs
    -0.84
     Monfieur
    -0.83
     greateſt
    -0.83
     ſmall
    -0.82
    POSITIVE LOGITS
     -
    0.53
     
    0.51
     ans
    0.50
     at
    0.48
    EdgeInsets
    0.48
     يلي
    0.48
     here
    0.46
    InjectAttribute
    0.46
     i
    0.45
     e
    0.45
    Act Density 0.028%

    No Known Activations