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

    Neuronpedia

    INDEX
    Explanations

    keywords related to historical events or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events and documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leased
    -0.75
    ressed
    -0.71
    achment
    -0.69
    ishable
    -0.69
    uppet
    -0.67
    ividual
    -0.66
    inki
    -0.65
    enger
    -0.65
    uster
    -0.65
    pher
    -0.64
    POSITIVE LOGITS
     buffs
    0.88
    orians
    0.76
     nostalg
    0.76
    ISTORY
    0.75
     Lith
    0.74
    making
    0.74
     tale
    0.73
     textbooks
    0.72
    ICAL
    0.71
     history
    0.70
    Act Density 0.030%

    No Known Activations