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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating a strong determination or intent

    oai_token-act-pair · gpt-3.5-turbo

    statements of existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dug
    -0.65
     Platform
    -0.65
    cius
    -0.63
    wen
    -0.63
    ribune
    -0.61
    ulkan
    -0.59
     Philippines
    -0.59
     Tribune
    -0.59
    powder
    -0.58
    mes
    -0.57
    POSITIVE LOGITS
     awfully
    0.76
     surely
    0.76
    ItemTracker
    0.74
    Ĥª
    0.71
     certainly
    0.70
    ¥µ
    0.69
    é¾įå¥ij士
    0.68
    ģĸ
    0.67
     understandably
    0.67
     undoubtedly
    0.66
    Act Density 0.288%

    No Known Activations