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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases related to love and emotions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jem
    -0.75
     seiz
    -0.71
     sights
    -0.67
     princ
    -0.66
     fortun
    -0.65
     photoc
    -0.62
     decomp
    -0.62
     NEO
    -0.62
     Customs
    -0.62
     commem
    -0.62
    POSITIVE LOGITS
    Ļ
    1.52
    ¤
    1.30
    ħ
    1.18
    ĺ
    1.16
    ĸ
    1.09
    Ĵ
    1.06
    ļ
    1.03
    ª
    1.02
    ı
    1.01
    ľ
    1.01
    Act Density 0.361%

    No Known Activations