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

    Neuronpedia

    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location "Corsica."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itably
    -0.83
    RED
    -0.73
    stakes
    -0.70
    LESS
    -0.67
    ded
    -0.66
    JECT
    -0.65
     Bain
    -0.65
    ted
    -0.64
    stage
    -0.64
    serving
    -0.64
    POSITIVE LOGITS
     Cors
    1.18
     corrid
    0.97
    airs
    0.87
    atell
    0.83
    illo
    0.82
    daq
    0.81
    inia
    0.80
     fortun
    0.79
    ando
    0.78
    imore
    0.77
    Act Density 0.007%

    No Known Activations