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

    Neuronpedia

    INDEX
    Explanations

    specific strings of special characters and words

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of specific non-standard or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fortun
    -0.88
     decomp
    -0.75
     interf
    -0.72
     Marketable
    -0.71
     embr
    -0.71
     Nex
    -0.69
     Obi
    -0.68
     Zup
    -0.68
     polyg
    -0.68
     Codec
    -0.68
    POSITIVE LOGITS
    ¢
    1.17
    Ļ
    1.16
    ¬
    1.13
    Ń
    1.05
    Ĵ
    1.05
    ª
    1.05
    ı
    1.02
    £
    1.00
    ¡
    0.99
    ħ
    0.98
    Act Density 0.402%

    No Known Activations