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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific place or person

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Burn" followed by various contexts and associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.74
    ngth
    -0.72
    ilial
    -0.70
     Schn
    -0.69
     NETWORK
    -0.66
    kson
    -0.63
    mercial
    -0.63
    prises
    -0.63
    FTWARE
    -0.61
    Grab
    -0.61
    POSITIVE LOGITS
    er
    1.07
    aby
    1.05
    ished
    1.00
    ards
    0.94
    lee
    0.91
    burn
    0.86
    ishing
    0.85
    iation
    0.84
    lett
    0.83
    ers
    0.81
    Act Density 0.027%

    No Known Activations