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

    Neuronpedia

    INDEX
    Explanations

    mentions of political and social news topics

    oai_token-act-pair · gpt-3.5-turbo

    commas and other punctuation marks, particularly focusing on their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.57
    Thumbnail
    -0.56
    venth
    -0.56
    minster
    -0.55
    Override
    -0.55
    cule
    -0.54
    eret
    -0.52
    phant
    -0.52
    oya
    -0.51
    viation
    -0.50
    POSITIVE LOGITS
     huh
    0.87
     wherein
    0.86
     namely
    0.84
     including
    0.82
     which
    0.76
     according
    0.76
     respectively
    0.76
     culminating
    0.74
     whereby
    0.73
     albeit
    0.73
    Act Density 0.413%

    No Known Activations