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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mous
    -0.75
     Manit
    -0.69
    anwhile
    -0.67
     princ
    -0.66
     Sprint
    -0.65
     Franch
    -0.62
     Albuquerque
    -0.61
     CMS
    -0.61
     Huntington
    -0.60
     sacrific
    -0.60
    POSITIVE LOGITS
    ľ
    1.56
    Ŀ
    1.30
    ¼
    1.22
    ¡
    1.18
    Ń
    1.13
    ¿
    1.11
    Ķ
    1.11
    °
    1.05
    ¦
    1.03
    âĶĢ
    1.03
    Act Density 0.255%

    No Known Activations