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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.12
     Majefty
    -1.11
     pleaſure
    -1.10
     raiſ
    -1.09
     myſelf
    -1.03
     itſelf
    -0.98
     ſever
    -0.98
     fevere
    -0.97
    AndEndTag
    -0.97
     Houſe
    -0.96
    POSITIVE LOGITS
     alternatively
    0.86
     else
    0.77
     even
    0.70
     же
    0.68
     just
    0.66
     simply
    0.65
     maybe
    0.63
     if
    0.62
    else
    0.60
     it
    0.59
    Act Density 0.164%

    No Known Activations