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

    Neuronpedia

    INDEX
    Explanations

    years and publishers of publications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to publication and authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.84
    anka
    -0.73
    itiveness
    -0.70
     briefed
    -0.68
     downed
    -0.68
     suited
    -0.67
    rious
    -0.67
    rounded
    -0.67
    iors
    -0.67
    wolves
    -0.66
    POSITIVE LOGITS
     Scrib
    0.89
     commem
    0.82
     conjunction
    0.81
     Springer
    0.80
     paperback
    0.80
     PBS
    0.79
     Spiegel
    0.76
    OUP
    0.71
     tandem
    0.70
     theaters
    0.70
    Act Density 0.201%

    No Known Activations