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

    Neuronpedia

    INDEX
    Explanations

    the use of prepositions and conjunctions that connect ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -1.18
     itſelf
    -1.17
     myſelf
    -1.11
     ſtate
    -1.10
     purpoſe
    -1.07
     pleaſure
    -1.01
     himſelf
    -1.01
     whoſe
    -0.98
     Efq
    -0.97
     uſed
    -0.95
    POSITIVE LOGITS
     the
    1.06
     a
    0.86
     an
    0.81
    ":
    0.79
    :
    0.79
     saites
    0.78
    "):
    0.78
     :
    0.78
    ():
    0.76
    =
    0.74
    Act Density 0.809%

    No Known Activations