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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "unn" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MX
    -0.76
    Journal
    -0.72
    league
    -0.71
    HER
    -0.67
     Cheong
    -0.65
     Alchemist
    -0.65
     Imran
    -0.64
    ccording
    -0.63
    quality
    -0.63
    ORGE
    -0.62
    POSITIVE LOGITS
    ipeg
    1.16
    umbered
    1.01
    unn
    0.98
    igan
    0.93
    itely
    0.92
    ified
    0.91
    ikuman
    0.90
    igham
    0.89
    ite
    0.89
    itory
    0.88
    Act Density 0.014%

    No Known Activations