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

    Neuronpedia

    INDEX
    Explanations

    sequences of comment or code delimiter characters in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.01
    #+#
    -0.97
     isComment
    -0.94
     PRD
    -0.93
     doubtnut
    -0.93
    makeConstraints
    -0.92
    principalColumn
    -0.91
     Charlemagne
    -0.90
     Concorde
    -0.86
     carreaux
    -0.83
    POSITIVE LOGITS
    ////////////////
    1.29
     //
    1.16
     #
    1.03
     ~
    1.01
    y
    0.91
    ي
    0.85
     ^
    0.82
     //$
    0.81
     Rosie
    0.78
    /////////
    0.77
    Act Density 0.099%

    No Known Activations