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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayne
    -0.87
    imilar
    -0.77
    cius
    -0.72
    adders
    -0.71
    fee
    -0.70
    laus
    -0.70
    sounding
    -0.69
    paren
    -0.68
    egal
    -0.68
    alos
    -0.68
    POSITIVE LOGITS
     columnist
    0.95
     publisher
    0.90
    lisher
    0.89
     archives
    0.88
     editor
    0.86
     newspapers
    0.85
     newspaper
    0.83
     Newsp
    0.81
     publishers
    0.80
     reporter
    0.78
    Act Density 0.018%

    No Known Activations