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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rosenthal
    -0.68
     Sar
    -0.62
     Spr
    -0.62
     Beck
    -0.60
     S
    -0.59
     Ba
    -0.59
     Lin
    -0.59
     Har
    -0.58
     J
    -0.58
     P
    -0.58
    POSITIVE LOGITS
     itſelf
    1.40
     Theſe
    1.35
     Anſ
    1.34
     Efq
    1.34
     Houſe
    1.27
     Reſ
    1.26
     Majefty
    1.25
     crdi
    1.24
     Monfieur
    1.23
     ―――――
    1.19
    Act Density 1.362%

    No Known Activations