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

    Neuronpedia

    INDEX
    Explanations

    titles or headings labeled as "Introduction."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Introduction."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.81
    rage
    -0.77
    rie
    -0.70
    rice
    -0.70
     saline
    -0.67
    roph
    -0.66
    riter
    -0.66
    rett
    -0.65
    urious
    -0.65
     opio
    -0.65
    POSITIVE LOGITS
    spection
    0.86
    matter
    0.80
    xual
    0.79
    ptions
    0.78
    spective
    0.75
     APR
    0.71
    PsyNetMessage
    0.70
    lectic
    0.70
    uador
    0.69
     Introduction
    0.69
    Act Density 0.020%

    No Known Activations