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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discussions and opinions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ominated
    -0.65
    irie
    -0.65
    haus
    -0.64
    rament
    -0.62
    hower
    -0.61
    oir
    -0.60
    ratulations
    -0.59
    iple
    -0.58
    robat
    -0.57
    sheet
    -0.57
    POSITIVE LOGITS
     noting
    1.20
     citing
    1.08
     adding
    1.02
     implying
    1.01
     stressing
    1.01
     namely
    0.92
     including
    0.90
     stating
    0.89
     referring
    0.88
     although
    0.86
    Act Density 0.436%

    No Known Activations