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

    Neuronpedia

    INDEX
    Explanations

    references to media outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eric
    -0.72
    ayne
    -0.72
    heed
    -0.70
    yles
    -0.65
    potion
    -0.65
    ening
    -0.62
     Defin
    -0.61
    ipeg
    -0.59
    icted
    -0.58
    nexus
    -0.58
    POSITIVE LOGITS
     outlets
    1.01
     outlet
    0.99
     ARTICLE
    0.73
     SPORTS
    0.70
    ="#
    0.68
     Wem
    0.68
     publishes
    0.68
    swick
    0.68
    independent
    0.67
    eval
    0.67
    Act Density 0.030%

    No Known Activations