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

    Neuronpedia

    INDEX
    Explanations

    countries starting with the letter "S"

    oai_token-act-pair · gpt-3.5-turbo

    country names and their associated identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sters
    -0.74
    etary
    -0.71
    PLIED
    -0.69
    -|
    -0.68
    JECT
    -0.68
    dress
    -0.67
    eless
    -0.67
    ortion
    -0.66
     Bei
    -0.66
    strong
    -0.65
    POSITIVE LOGITS
    ines
    0.95
    ice
    0.76
    imoto
    0.75
    inia
    0.74
    ansk
    0.73
    atton
    0.71
    idation
    0.71
    INE
    0.70
    ider
    0.70
    idate
    0.69
    Act Density 0.076%

    No Known Activations