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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that appear repeatedly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.74
     NEC
    -0.73
     photoc
    -0.69
     swept
    -0.68
    çīĪ
    -0.66
     fed
    -0.65
    anwhile
    -0.65
     Kob
    -0.63
     MET
    -0.61
     Shib
    -0.61
    POSITIVE LOGITS
    ¢
    0.93
    §
    0.90
    £
    0.90
    ¬
    0.89
    ¹
    0.89
    ¿
    0.87
    Ĵ
    0.86
    ¼
    0.84
    ¦
    0.83
    º
    0.83
    Act Density 0.294%

    No Known Activations