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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and other symbols used in text formatting or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.02
     Theſe
    -0.96
     ་་
    -0.96
     Reſ
    -0.93
     propOrder
    -0.90
     doubtnut
    -0.89
     itſelf
    -0.86
     Forumite
    -0.86
     raiſ
    -0.86
     faſt
    -0.86
    POSITIVE LOGITS
    ,
    0.77
    !
    0.66
    </sup>
    0.63
    )
    0.63
     =
    0.62
    -
    0.59
    </sub>
    0.58
     and
    0.57
    </em>
    0.56
    </code>
    0.53
    Act Density 1.235%

    No Known Activations