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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.56
     Efq
    -1.50
     Jefus
    -1.47
     purpoſe
    -1.44
     himſelf
    -1.41
     myſelf
    -1.40
     poffible
    -1.39
     houſe
    -1.35
     Majefty
    -1.35
     uſed
    -1.32
    POSITIVE LOGITS
     And
    1.04
     và
    0.99
     AND
    0.98
     and
    0.96
    /
    0.92
     \&
    0.86
    \&
    0.85
    Và
    0.85
     och
    0.84
     и
    0.84
    Act Density 1.383%

    No Known Activations