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

    Neuronpedia

    INDEX
    Explanations

    phrases highlighting positive aspects or features of various entities

    oai_token-act-pair · gpt-3.5-turbo

    discussions highlighting the notable or interesting aspects of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STATE
    -0.77
    DERR
    -0.76
    mouth
    -0.73
    bus
    -0.72
    whe
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    COL
    -0.68
    />
    -0.66
    lli
    -0.65
    OIL
    -0.65
    POSITIVE LOGITS
     Kinnikuman
    0.75
    ©¶æ
    0.70
    anium
    0.67
     Antar
    0.67
     this
    0.66
    lihood
    0.65
    adding
    0.64
     Nug
    0.62
     deploying
    0.61
     these
    0.60
    Act Density 0.172%

    No Known Activations