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

    Neuronpedia

    INDEX
    Explanations

    numerical values and punctuation within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.76
    GEBURTSDATUM
    -0.73
    rungsseite
    -0.70
    \#:
    -0.67
     Shakspeare
    -0.66
     myſelf
    -0.66
     himſelf
    -0.65
    ]!='
    -0.61
     degeneracy
    -0.59
     itſelf
    -0.59
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵↵↵↵
    0.50
     Winaray
    0.50
    DrawerToggle
    0.49
     برانيه
    0.48
     henvisninger
    0.47
    Tembelea
    0.46
    MemoryWarning
    0.46
    ↵↵↵↵↵↵
    0.46
    UpInside
    0.45
    Act Density 0.065%

    No Known Activations