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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "mann" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.71
    ngth
    -0.70
    WHERE
    -0.69
     welf
    -0.67
    rip
    -0.65
    =-=-=-=-
    -0.65
    bound
    -0.64
     Citiz
    -0.62
    cess
    -0.62
    vette
    -0.61
    POSITIVE LOGITS
    mann
    0.97
    elson
    0.90
    strom
    0.90
    enegger
    0.86
    otti
    0.84
    ufact
    0.83
    ogl
    0.79
    stein
    0.79
    ophon
    0.78
    gart
    0.78
    Act Density 0.022%

    No Known Activations