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

    dialogs and quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦"
    -1.01
    –
    -1.00
    ÃĹ
    -0.91
    "âĢ¦
    -0.91
     –
    -0.89
    Advertisements
    -0.88
    âĢ¦
    -0.85
    âĢ³
    -0.84
     ðŁĻĤ
    -0.68
    âĢ¦."
    -0.68
    POSITIVE LOGITS
     ''
    4.09
     ``
    2.51
     �
    2.35
     \"
    1.63
    ''
    1.63
     ""
    1.53
     âĢİ
    1.52
    .''
    1.52
     «
    1.51
     `
    1.46
    Act Density 0.016%

    No Known Activations