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

    Neuronpedia

    INDEX
    Explanations

    references to historians in text

    oai_token-act-pair · gpt-3.5-turbo

    references to historians and scholarly analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ply
    -0.80
    chy
    -0.80
    arter
    -0.76
    pose
    -0.72
     Lumpur
    -0.72
     unconditional
    -0.72
    ramid
    -0.70
    cheon
    -0.69
    eat
    -0.68
    legate
    -0.68
    POSITIVE LOGITS
     historian
    1.24
     historians
    1.13
     nostalg
    1.04
     buffs
    0.92
     archaeologists
    0.86
    abilia
    0.86
    orically
    0.85
     histor
    0.84
    orians
    0.83
     scholar
    0.81
    Act Density 0.011%

    No Known Activations