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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and economic topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas, indicating lists or pauses in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eus
    -0.62
    iously
    -0.61
    Laughs
    -0.60
    »
    -0.60
    dragon
    -0.58
    ãĥ¥
    -0.58
    laughs
    -0.58
    ").
    -0.57
    eny
    -0.56
    phant
    -0.56
    POSITIVE LOGITS
     meanwhile
    1.12
     however
    0.91
    channelAvailability
    0.84
    utherford
    0.82
     namely
    0.79
     including
    0.79
     coupled
    0.78
     huh
    0.76
    ppelin
    0.75
     moreover
    0.75
    Act Density 0.558%

    No Known Activations