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

    Neuronpedia

    INDEX
    Explanations

    method calls and property access within programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </b>
    -0.59
     
    -0.57
     [
    -0.56
    </u>
    -0.56
    </i>
    -0.54
    </strong>
    -0.54
    <i>
    -0.51
     &
    -0.49
    </sup>
    -0.49
    <em>
    -0.48
    POSITIVE LOGITS
     houſe
    1.04
     ſtate
    1.01
     pleaſure
    0.98
     ſeveral
    0.97
     Jefus
    0.96
     Efq
    0.96
     RIPRODUZIONE
    0.96
     itſelf
    0.94
     Majefty
    0.90
     purpoſe
    0.90
    Act Density 0.072%

    No Known Activations