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

    Neuronpedia

    INDEX
    Explanations

    phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotations or speech marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.75
    odon
    -0.72
    uga
    -0.69
     spar
    -0.68
    ments
    -0.67
     parcel
    -0.65
    zin
    -0.64
    cients
    -0.63
    roc
    -0.62
     staggered
    -0.62
    POSITIVE LOGITS
    /"
    1.28
    Reply
    0.95
    >>\
    0.90
     ..."
    0.89
    }"
    0.86
     />
    0.86
    False
    0.78
     ["
    0.78
    ""
    0.74
    Yeah
    0.74
    Act Density 0.083%

    No Known Activations