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

    Neuronpedia

    INDEX
    Explanations

    repeated sections or patterns in the text, particularly the use of equality or assignment symbols in code syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Meksiku
    -1.26
     تانيه
    -1.04
    lwjgl
    -0.97
    ///</
    -0.86
     @"/
    -0.85
    WebpackPlugin
    -0.85
    basicConfig
    -0.84
     Chiron
    -0.83
     Sardinia
    -0.82
     Dumbledore
    -0.81
    POSITIVE LOGITS
     ===
    1.37
     !==
    1.13
    ===
    1.05
    !==
    0.97
    <?=
    0.89
    راً
    0.77
    Darren
    0.76
    ര്‍
    0.75
    ماً
    0.74
    ="<?=
    0.72
    Act Density 0.005%

    No Known Activations