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

    Neuronpedia

    INDEX
    Explanations

    dates expressed as day and month

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.86
     challeng
    -0.84
     disadvant
    -0.75
     oun
    -0.74
     outsider
    -0.73
     glim
    -0.72
     ethn
    -0.72
     interf
    -0.71
     temperament
    -0.68
     awakening
    -0.68
    POSITIVE LOGITS
    php
    0.98
    jpg
    0.98
     Please
    0.96
    txt
    0.95
     Subscribe
    0.89
    icio
    0.87
     Cannot
    0.86
    google
    0.85
    html
    0.83
    aspx
    0.83
    Act Density 0.207%

    No Known Activations