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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or financial matters

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pyramid
    -0.86
    PU
    -0.85
    ulhu
    -0.83
    ongyang
    -0.81
    ramid
    -0.79
     PU
    -0.76
     umb
    -0.75
     sep
    -0.75
     Nou
    -0.74
     membranes
    -0.73
    POSITIVE LOGITS
     Beck
    1.69
    Hart
    1.60
     Hart
    1.59
    Beck
    1.53
     Taylor
    1.35
    Taylor
    1.20
     Ort
    1.19
     Lund
    1.03
     Becky
    1.03
     Brock
    1.02
    Act Density 0.346%

    No Known Activations