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

    Neuronpedia

    INDEX
    Explanations

    mentions of statistical data and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "according to" which indicates sources or references in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.88
     eleph
    -0.81
     submar
    -0.78
     helicop
    -0.65
     conclud
    -0.64
     fuss
    -0.62
    otor
    -0.62
    ²¾
    -0.61
    Þ
    -0.61
    ailability
    -0.59
    POSITIVE LOGITS
     to
    0.91
     Nielsen
    0.78
     surveys
    0.77
     estimates
    0.74
     Reuters
    0.69
     Census
    0.68
    %]
    0.68
     POLITICO
    0.68
     data
    0.68
     Gallup
    0.67
    Act Density 0.042%

    No Known Activations