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

    Neuronpedia

    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tradem
    -0.67
     rall
    -0.64
    etheless
    -0.63
     mathemat
    -0.63
     abduct
    -0.62
     agre
    -0.62
     exting
    -0.61
     steroids
    -0.59
     outsourcing
    -0.59
     newcom
    -0.59
    POSITIVE LOGITS
    soDeliveryDate
    0.91
    no
    0.88
    I
    0.87
    false
    0.86
    true
    0.83
    Hey
    0.82
    die
    0.82
    classic
    0.81
    don
    0.81
    nothing
    0.81
    Act Density 0.147%

    No Known Activations