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

    Neuronpedia

    INDEX
    Explanations

    locations or places with the suffix "-ham"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ham" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atively
    -0.72
    ahead
    -0.72
    iquid
    -0.65
    emort
    -0.61
    ELF
    -0.61
    UID
    -0.58
    Magikarp
    -0.58
    vier
    -0.58
    REDACTED
    -0.57
    enhagen
    -0.57
    POSITIVE LOGITS
    pton
    1.67
    mers
    1.41
    ilton
    1.29
    monds
    1.28
    mond
    1.26
    sburg
    1.16
    ming
    1.12
    med
    1.08
    shire
    1.08
    MER
    1.08
    Act Density 0.042%

    No Known Activations