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

    Neuronpedia

    INDEX
    Explanations

    names or terms with special characters, such as accents or non-English letters

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent political figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hunts
    -0.64
     rear
    -0.63
     messages
    -0.61
     jobs
    -0.60
    market
    -0.60
     Liberty
    -0.58
     store
    -0.58
     Meg
    -0.58
     SEC
    -0.58
     storage
    -0.58
    POSITIVE LOGITS
    Äĩ
    5.35
    Äį
    2.60
    Å¡
    1.89
    ÅŁ
    1.75
    ÅĤ
    1.69
    ÄŁ
    1.63
     Croatian
    1.52
    kson
    1.50
    tsky
    1.43
    ovic
    1.42
    Act Density 0.015%

    No Known Activations