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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific formatting or code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.50
    ↵
    -0.48
    <eos>
    -0.47
    ↵↵
    -0.43
     Masse
    -0.43
    fetchone
    -0.42
    就是
    -0.42
     handle
    -0.41
    що
    -0.41
    彦
    -0.41
    POSITIVE LOGITS
    enumi
    0.98
    neſs
    0.90
    ſelves
    0.89
    enumii
    0.84
     itſelf
    0.83
     Houſe
    0.82
     Мексичка
    0.82
     Anſ
    0.82
     purpoſe
    0.82
    Portail
    0.82
    Act Density 0.017%

    No Known Activations