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

    Neuronpedia

    INDEX
    Explanations

    phrases containing direct speech where someone is speaking to another person

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "said to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fractures
    -0.68
    irez
    -0.62
    closed
    -0.61
     netted
    -0.60
    grounds
    -0.60
     deductions
    -0.58
     botched
    -0.57
     exemptions
    -0.57
     contested
    -0.56
    soDeliveryDate
    -0.56
    POSITIVE LOGITS
    wered
    1.05
     me
    0.94
    speak
    0.85
    ilet
    0.81
     us
    0.80
    asts
    0.79
     him
    0.77
    pless
    0.77
    ggles
    0.77
     imitate
    0.76
    Act Density 0.082%

    No Known Activations