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

    Neuronpedia

    INDEX
    Explanations

    delimited text blocks ending with a period inside quotation marks and possibly followed by some form of attribution

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enriched
    -0.76
     contrace
    -0.73
     paran
    -0.71
    lements
    -0.70
    imates
    -0.67
    ocating
    -0.67
    bably
    -0.67
     conditioned
    -0.67
    mber
    -0.66
    odka
    -0.65
    POSITIVE LOGITS
     âĢķ
    0.95
     Speak
    0.86
     Said
    0.81
     Hearing
    0.78
    >>\
    0.75
     Listen
    0.74
     ãĢĮ
    0.74
     Accord
    0.74
     Tears
    0.73
    Weak
    0.72
    Act Density 0.094%

    No Known Activations