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

    Neuronpedia

    INDEX
    Explanations

    strings of characters in different alphabets, possibly related to computer code or languages with special characters

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "¯" or variations of it, suggesting it can identify repeated or styled characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nex
    -0.75
     Liqu
    -0.69
     Wed
    -0.67
     Viv
    -0.67
     Wear
    -0.66
     Scrib
    -0.66
    guard
    -0.66
     shares
    -0.65
     lockout
    -0.63
     den
    -0.63
    POSITIVE LOGITS
    ¯
    4.46
    ®
    2.14
    ª
    1.82
    Ń
    1.81
    ¬
    1.80
    ¦
    1.74
    °
    1.74
    Ł
    1.72
    ²
    1.71
    £
    1.70
    Act Density 0.011%

    No Known Activations