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

    Neuronpedia

    INDEX
    Explanations

    information about news, weather, and events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Antiqu
    -0.67
     Anthrop
    -0.61
    ueless
    -0.61
    ignt
    -0.59
     somew
    -0.59
    ©¶æ¥µ
    -0.59
     antiqu
    -0.58
    uable
    -0.58
    igi
    -0.58
    udes
    -0.57
    POSITIVE LOGITS
    letters
    1.03
    flash
    1.02
    room
    0.98
    letter
    0.89
    worthy
    0.88
    LET
    0.86
    groups
    0.86
    rooms
    0.86
    worthiness
    0.84
    feed
    0.81
    Act Density 0.018%

    No Known Activations