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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and coordinating conjunction phrases that indicate contrast or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.00
    ſelf
    -0.98
     Diſ
    -0.97
     Monfieur
    -0.97
     itſelf
    -0.97
     Theſe
    -0.96
     myſelf
    -0.95
     themſelves
    -0.94
     تضيفلها
    -0.93
     pleaſure
    -0.91
    POSITIVE LOGITS
     And
    0.63
    And
    0.54
    Lähteet
    0.48
     Or
    0.45
     it
    0.42
    -
    0.42
     J
    0.41
    ,
    0.41
     M
    0.41
     Plus
    0.41
    Act Density 0.336%

    No Known Activations