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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offering a perspective or opinion on a topic

    oai_token-act-pair · gpt-3.5-turbo

    references to different perspectives or interpretations (takes) on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     constitu
    -0.77
    ĺħ
    -0.75
     Aires
    -0.69
     Buildings
    -0.68
     certific
    -0.67
     obser
    -0.65
    eger
    -0.65
     Places
    -0.65
     Standards
    -0.63
     thous
    -0.62
    POSITIVE LOGITS
    away
    1.29
    aways
    1.14
    over
    1.05
    athon
    1.03
    able
    1.02
    back
    1.00
    backs
    0.99
    ings
    0.97
    outs
    0.93
    ability
    0.92
    Act Density 0.272%

    No Known Activations