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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or entities named "Burn" followed by numerical values that indicate some kind of significance or relation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Burnham" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilial
    -0.73
    DonaldTrump
    -0.71
    mercial
    -0.66
     FINAL
    -0.66
    ploma
    -0.65
    ngth
    -0.65
    awaru
    -0.65
    ournal
    -0.64
    ensional
    -0.64
    ocre
    -0.62
    POSITIVE LOGITS
    burn
    1.01
    ished
    0.99
    er
    0.90
    aby
    0.90
    Burn
    0.90
    ards
    0.89
     Burn
    0.88
    burning
    0.86
    ishing
    0.82
     burn
    0.81
    Act Density 0.016%

    No Known Activations