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

    Neuronpedia

    INDEX
    Explanations

    characters from non-Latin alphabets along with some English words and phrases, possibly related to historical or cultural contexts

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly from non-Latin scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nels
    -0.77
     dope
    -0.77
     agre
    -0.71
    sterdam
    -0.70
     Blitz
    -0.69
    nyder
    -0.68
    nell
    -0.66
    eln
    -0.66
    ftime
    -0.66
     Miss
    -0.64
    POSITIVE LOGITS
    ŃĶ
    1.18
    ľ
    1.05
    ł
    1.05
    ĵ
    1.04
    ĨĴ
    1.02
    «ĺ
    1.02
    Ļ
    1.02
    Ĵ
    1.00
    ħ
    1.00
    å
    0.99
    Act Density 0.011%

    No Known Activations