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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to user interface elements and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.63
    ↵↵↵↵
    -0.61
     li
    -0.59
    ↵↵↵
    -0.57
     }
    -0.56
    تقاوى
    -0.55
    .
    -0.54
    ↵↵↵↵↵
    -0.53
    Abstract
    -0.52
     “
    -0.52
    POSITIVE LOGITS
     Efq
    1.09
     Jefus
    1.05
     Theſe
    1.04
     ſtate
    1.02
     chofe
    1.02
     houſe
    1.01
     greateſt
    1.01
     purpoſe
    0.98
     itſelf
    0.96
     myſelf
    0.96
    Act Density 0.017%

    No Known Activations