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

    Neuronpedia

    INDEX
    Explanations

    personal opinions or narratives

    oai_token-act-pair · gpt-3.5-turbo

    references to opinions or critiques in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.82
    ogether
    -0.81
     blat
    -0.76
     traged
    -0.75
    akespe
    -0.74
     encour
    -0.74
    entimes
    -0.73
    anwhile
    -0.73
     [*
    -0.72
    ierrez
    -0.71
    POSITIVE LOGITS
     âĢº
    0.97
     Vegan
    0.80
     Raspberry
    0.74
     Updated
    0.70
     Hearthstone
    0.69
     Anime
    0.69
     Belfast
    0.67
     ][
    0.66
     Introduction
    0.65
     Podcast
    0.65
    Act Density 1.104%

    No Known Activations