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

    Neuronpedia

    INDEX
    Explanations

    words related to sustainability and self-sustainability

    oai_token-act-pair · gpt-3.5-turbo

    the concept of sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.64
    manship
    -0.61
    cks
    -0.59
    zig
    -0.59
     derog
    -0.57
    plin
    -0.57
    pl
    -0.57
    Bon
    -0.57
    ck
    -0.56
    wcs
    -0.56
    POSITIVE LOGITS
    rations
    1.12
    rious
    1.09
    rine
    1.08
    rator
    1.08
    ral
    1.05
    rans
    1.04
    rated
    1.04
    ained
    1.04
    roph
    1.02
    ribut
    0.99
    Act Density 0.038%

    No Known Activations