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

    Neuronpedia

    INDEX
    Explanations

    phrases related to infrastructure and societal improvement

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.70
    ģ«
    -0.68
    atically
    -0.68
    ¬¼
    -0.66
    atus
    -0.66
    achev
    -0.61
     Whale
    -0.60
    ouver
    -0.59
    eteen
    -0.59
    lor
    -0.58
    POSITIVE LOGITS
    anwhile
    0.74
     including
    0.72
     etc
    0.65
     Addiction
    0.65
    doms
    0.64
     namely
    0.62
    nutrition
    0.62
    tein
    0.61
     Including
    0.60
     disabilities
    0.58
    Act Density 0.465%

    No Known Activations