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

    Neuronpedia

    INDEX
    Explanations

    references to specific publications

    oai_token-act-pair · gpt-3.5-turbo

    references to media publications, particularly Forbes and Rolling Stone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    until
    -0.75
    displayText
    -0.69
    unts
    -0.69
     concession
    -0.66
    ardless
    -0.65
    train
    -0.65
    rar
    -0.62
    abiding
    -0.62
    cue
    -0.61
    artifacts
    -0.60
    POSITIVE LOGITS
     Magazine
    1.72
     magazine
    1.65
    Magazine
    1.41
     magazines
    1.07
     Publishing
    1.01
    azine
    0.95
     columnist
    0.95
     Monthly
    0.94
     Weekly
    0.93
     Illustrated
    0.91
    Act Density 0.172%

    No Known Activations