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

    Neuronpedia

    INDEX
    Explanations

    names of locations or individuals, possibly with a Caribbean connection

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    train
    -0.92
    EVA
    -0.74
    lihood
    -0.74
    VEN
    -0.72
    lder
    -0.70
    ffic
    -0.70
    VOL
    -0.69
    vent
    -0.69
    share
    -0.68
    nder
    -0.68
    POSITIVE LOGITS
    ados
    1.07
     Barb
    1.01
    adoes
    0.96
    adian
    0.94
    ican
    0.93
    izon
    0.89
    uda
    0.83
    abies
    0.81
    adeon
    0.80
    icans
    0.79
    Act Density 0.005%

    No Known Activations