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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusive statements or summaries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "there's no" followed by various statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mun
    -0.68
     Kenyan
    -0.66
     Mansion
    -0.64
    Buyable
    -0.63
     Paras
    -0.62
     juggling
    -0.62
    vt
    -0.61
     hob
    -0.61
     cyan
    -0.60
     Mush
    -0.60
    POSITIVE LOGITS
    £
    1.04
    º
    0.99
    Ĵ
    0.86
    abad
    0.86
    ¹
    0.84
    ¬
    0.84
    ı
    0.83
    ihad
    0.78
    ¼
    0.77
    Ń
    0.77
    Act Density 0.038%

    No Known Activations