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

    Neuronpedia

    INDEX
    Explanations

    phrases related to familiarity with a topic or subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating familiarity with various subjects or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teasp
    -0.65
    earchers
    -0.61
     enthusi
    -0.59
    ratulations
    -0.59
    \/\/
    -0.58
     surprised
    -0.57
     Sabha
    -0.57
    OGR
    -0.57
    nette
    -0.56
    orah
    -0.55
    POSITIVE LOGITS
    ¥µ
    0.92
     firsthand
    0.85
    stood
    0.83
     whats
    0.81
    ä¹
    0.70
     how
    0.68
     Pastebin
    0.67
     regards
    0.67
     Runes
    0.66
     whom
    0.66
    Act Density 0.056%

    No Known Activations