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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.55
     os
    -0.53
     pag
    -0.52
     Pugh
    -0.50
    Démographie
    -0.49
    MEDIATE
    -0.49
     nämlich
    -0.47
     Dickerson
    -0.47
    ΗΣ
    -0.46
    xH
    -0.46
    POSITIVE LOGITS
     itſelf
    0.77
     myſelf
    0.75
    0.75
     poffible
    0.74
     ſeveral
    0.74
     fubject
    0.74
     himſelf
    0.73
     raiſ
    0.71
     Мексичка
    0.70
     purpoſe
    0.70
    Act Density 0.039%

    No Known Activations