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

    Neuronpedia

    INDEX
    Explanations

    code-related comments and function declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.01
    HomeAsUpEnabled
    -1.00
     uſed
    -0.98
     Efq
    -0.98
     ſeveral
    -0.97
    ſelf
    -0.96
     reaſon
    -0.94
     raiſ
    -0.94
    ConstraintMaker
    -0.93
     auffi
    -0.92
    POSITIVE LOGITS
      
    0.72
    <eos>
    0.53
    0.53
     R
    0.53
     specific
    0.51
     
    0.51
     de
    0.50
     data
    0.50
     V
    0.49
     Ex
    0.49
    Act Density 0.136%
    No Known Activations