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

    Neuronpedia

    INDEX
    Explanations

    Japanese characters and their combinations

    oai_token-act-pair · gpt-3.5-turbo

    special characters and unique symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.94
    raviolet
    -0.85
    undai
    -0.83
    etsk
    -0.83
    rongh
    -0.82
    merce
    -0.80
    orsche
    -0.79
    raints
    -0.78
    ernels
    -0.77
    eatures
    -0.75
    POSITIVE LOGITS
    å®
    1.25
    åº
    1.20
    ç
    1.20
    ãģ®
    1.17
    è¡
    1.17
    åħ
    1.16
    ãģ
    1.16
    å
    1.16
    åŃIJ
    1.15
    éĩ
    1.15
    Act Density 0.137%

    No Known Activations