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

    Neuronpedia

    INDEX
    Explanations

    quoted statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotations or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conflic
    -0.62
    theless
    -0.61
    estine
    -0.61
     marginal
    -0.61
    tan
    -0.58
    otin
    -0.58
    avour
    -0.56
    idates
    -0.56
    peat
    -0.55
    ptin
    -0.55
    POSITIVE LOGITS
     Wednesday
    1.04
     Thursday
    1.03
     Tuesday
    1.03
     Monday
    1.03
     afterward
    0.99
     Friday
    0.96
     via
    0.82
     Sunday
    0.81
     TODAY
    0.81
     Saturday
    0.80
    Act Density 0.113%

    No Known Activations