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

    Neuronpedia

    INDEX
    Explanations

    words related to large-scale and significant events or actions, often with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mass" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.84
    thy
    -0.72
    gers
    -0.72
    mins
    -0.71
    ĪĴ
    -0.71
    bors
    -0.70
    ilk
    -0.69
    thens
    -0.68
    poons
    -0.67
    warts
    -0.67
    POSITIVE LOGITS
    achusetts
    1.32
     transit
    0.91
    aging
    0.90
    achus
    0.90
    acre
    0.89
     incarceration
    0.88
    ages
    0.84
     exodus
    0.84
    imil
    0.84
     mobilization
    0.82
    Act Density 0.037%

    No Known Activations