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

    Neuronpedia

    INDEX
    Explanations

    mentions of newspapers

    oai_token-act-pair · gpt-3.5-turbo

    references to newspapers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umph
    -0.76
    dh
    -0.69
    adders
    -0.68
    paren
    -0.68
    cius
    -0.67
    cffffcc
    -0.67
    ayne
    -0.66
    lua
    -0.66
    alli
    -0.65
    acted
    -0.65
    POSITIVE LOGITS
     publisher
    1.00
     newspaper
    0.98
     columnist
    0.93
     editor
    0.93
     newspapers
    0.93
    lisher
    0.87
     publishers
    0.87
     Newspaper
    0.83
     magazine
    0.83
     archives
    0.82
    Act Density 0.013%

    No Known Activations