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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming and literature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technical specifications and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     marijuana
    -0.61
     [âĢ¦]
    -0.61
     business
    -0.59
     businesses
    -0.58
     returning
    -0.57
    lot
    -0.56
     sports
    -0.56
     agriculture
    -0.56
     grain
    -0.55
     cannabis
    -0.55
    POSITIVE LOGITS
    ragon
    0.96
    ulhu
    0.77
    anamo
    0.74
     Azerb
    0.73
    idia
    0.71
     Wraith
    0.71
    REDACTED
    0.69
     Tome
    0.69
    foundland
    0.68
    cember
    0.68
    Act Density 0.352%

    No Known Activations