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

    Neuronpedia

    INDEX
    Explanations

    the symbol 'âĢ'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.87
     snail
    -0.83
     Isle
    -0.77
     Nanto
    -0.74
     Lerner
    -0.73
     Mayo
    -0.72
     Ler
    -0.69
     Pirate
    -0.69
     Lou
    -0.68
     mainland
    -0.67
    POSITIVE LOGITS
    Ŀ
    1.91
    ¡
    1.49
    °
    1.35
    ¦
    1.33
    ŀ
    1.31
    ª
    1.29
    ©
    1.29
    §
    1.22
    ī
    1.21
    «
    1.21
    Act Density 0.235%

    No Known Activations