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

    Neuronpedia

    INDEX
    Explanations

    unusual characters or symbols from the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific repeated character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tanz
    -0.75
     captives
    -0.69
     dissidents
    -0.65
     Gaul
    -0.64
     Canadians
    -0.61
     vulner
    -0.59
     Palestin
    -0.59
     Lowell
    -0.58
     Stuff
    -0.58
     Mobil
    -0.58
    POSITIVE LOGITS
    ï¸ı
    0.85
    ï¸
    0.81
    own
    0.80
    Pg
    0.75
    uable
    0.75
    should
    0.73
    ished
    0.73
    forth
    0.71
    ved
    0.71
    imgur
    0.70
    Act Density 0.177%

    No Known Activations