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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    specific animal names and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.93
    ector
    -0.84
    anmar
    -0.76
    thood
    -0.74
    colo
    -0.71
    amic
    -0.71
    Ħ¢
    -0.70
    ietal
    -0.70
    namese
    -0.68
    acity
    -0.66
    POSITIVE LOGITS
    MQ
    0.91
     Rapids
    0.88
     Moose
    0.87
     Prairie
    0.80
    minster
    0.79
     Meadow
    0.76
    glers
    0.76
    wood
    0.76
    tail
    0.75
     Elm
    0.74
    Act Density 0.019%

    No Known Activations