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

    Neuronpedia

    INDEX
    Explanations

    references to newspapers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newspapers and their various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayne
    -0.83
    reek
    -0.73
    orsi
    -0.72
    eri
    -0.71
    fee
    -0.71
    ensis
    -0.69
    onite
    -0.69
    roxy
    -0.69
    imus
    -0.68
     Skywalker
    -0.67
    POSITIVE LOGITS
     columnist
    0.96
     articles
    0.94
     editor
    0.90
     clipping
    0.86
     archives
    0.86
     editors
    0.85
     newspapers
    0.81
     publisher
    0.80
     advertisements
    0.79
     tabl
    0.79
    Act Density 0.040%

    No Known Activations