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

    Neuronpedia

    INDEX
    Explanations

    data-related terms such as numbers, research results, and statistical findings

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data or statistics related to populations and societal trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yours
    -0.72
    quished
    -0.68
     confir
    -0.68
    enment
    -0.68
    aye
    -0.68
     comrade
    -0.65
     ours
    -0.64
    !).
    -0.63
    !/
    -0.63
    !'
    -0.62
    POSITIVE LOGITS
     "âĢ¦
    0.93
     "[
    0.84
     median
    0.81
     overest
    0.79
     clustered
    0.77
     respondents
    0.77
     underestimated
    0.76
     statistically
    0.75
    Compared
    0.74
    ificantly
    0.74
    Act Density 0.620%

    No Known Activations