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

    Neuronpedia

    INDEX
    Explanations

    words related to physical proximity or closeness

    oai_token-act-pair · gpt-3.5-turbo

    references to physical or metaphorical closeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Population
    -0.70
     Immunity
    -0.68
     Dhabi
    -0.67
     Curve
    -0.66
     Valencia
    -0.65
     Uzbek
    -0.65
     Commonwealth
    -0.65
    Rush
    -0.65
    District
    -0.64
    Stage
    -0.64
    POSITIVE LOGITS
    eness
    1.21
     clos
    1.13
    ety
    0.99
    uers
    0.98
    itiz
    0.92
    essed
    0.89
    owship
    0.87
    eties
    0.86
    otyp
    0.84
    atural
    0.84
    Act Density 0.015%

    No Known Activations