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

    Neuronpedia

    INDEX
    Explanations

    phrases related to arguments or opinions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.68
     isolate
    -0.62
    interstitial
    -0.62
     satell
    -0.59
     arrang
    -0.57
     active
    -0.57
    itiz
    -0.56
     surpr
    -0.56
     flank
    -0.56
    iets
    -0.56
    POSITIVE LOGITS
    ï¸ı
    1.02
    lished
    0.88
    Ö¼
    0.75
    ================================================================
    0.74
    ulhu
    0.71
    ONSORED
    0.71
    _-
    0.70
    lux
    0.70
    -----------
    0.69
    IVERS
    0.68
    Act Density 0.161%

    No Known Activations