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

    Neuronpedia

    INDEX
    Explanations

    political statements or comments

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly related to emotive expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remed
    -0.75
     semic
    -0.75
     dispers
    -0.73
     Siem
    -0.73
     steril
    -0.70
     sterile
    -0.70
     commercially
    -0.70
     prepar
    -0.68
     transfer
    -0.67
     subsistence
    -0.67
    POSITIVE LOGITS
    ª
    1.40
    ¹
    1.34
    ¬
    1.29
    ı
    1.27
    ½
    1.23
    ®
    1.22
    ¼
    1.22
    į
    1.19
    Ń
    1.18
    Į
    1.15
    Act Density 0.350%

    No Known Activations