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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that denote special or unusual characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-standard or special symbols in text.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    -
    -0.61
     Ad
    -0.59
     ad
    -0.58
     vara
    -0.58
     scha
    -0.58
    er
    -0.56
    te
    -0.54
     ver
    -0.53
    ver
    -0.53
     Ver
    -0.53
    POSITIVE LOGITS
    
    1.16
     Jefus
    1.12
     itſelf
    1.09
     myſelf
    1.07
    ſelf
    1.07
    
    1.03
     ſtate
    1.02
     Houſe
    1.01
     ་་
    1.01
    ſelves
    0.99
    Act Density 0.112%

    No Known Activations