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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and relational language indicating connections or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.38
     houſe
    -1.33
     Efq
    -1.31
     purpoſe
    -1.28
     ſtand
    -1.28
     myſelf
    -1.26
     auffi
    -1.26
    Vidite
    -1.26
     pleaſure
    -1.25
     itſelf
    -1.24
    POSITIVE LOGITS
    <eos>
    0.77
     
    0.75
     I
    0.72
    </i>
    0.71
     P
    0.69
     E
    0.65
    ↵↵
    0.65
     ap
    0.64
     F
    0.64
     a
    0.63
    Act Density 0.842%

    No Known Activations