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

    Neuronpedia

    INDEX
    Explanations

    the presence of whitespace or blank spaces in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -1.00
    ^(@)
    -0.96
     FontWeight
    -0.93
    Datuak
    -0.86
     useAuth
    -0.86
    udadera
    -0.85
    CloseOperation
    -0.84
    ſcher
    -0.84
    -0.81
    &
    -0.81
    POSITIVE LOGITS
    ↵↵
    1.45
    ↵
    1.08
    <eos>
    0.95
    ↵↵↵
    0.93
    ↵↵↵↵
    0.83
    ↵↵↵↵↵
    0.74
    ↵↵↵↵↵↵
    0.67
    </h3>
    0.67
    </blockquote>
    0.63
     The
    0.60
    Act Density 0.054%

    No Known Activations