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

    Neuronpedia

    INDEX
    Explanations

    ​diacritical marks like "ê" which may indicate specific character sets or accents in text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that indicate specific cultural references or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zimmerman
    -0.81
     Baltimore
    -0.79
     Rangers
    -0.70
     financially
    -0.70
     decks
    -0.69
     Compton
    -0.68
     Maryland
    -0.66
     Penn
    -0.66
     Deck
    -0.66
     LS
    -0.65
    POSITIVE LOGITS
    ê
    4.70
    î
    1.92
    ô
    1.74
    ë
    1.69
    ã
    1.62
    û
    1.52
    â
    1.43
    è
    1.42
    Äĵ
    1.39
    ét
    1.38
    Act Density 0.018%

    No Known Activations