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

    Neuronpedia

    INDEX
    Explanations

    commands prompting to take action or subscribe for updates

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or prompts for the reader to engage with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pard
    -0.64
     disson
    -0.60
    handedly
    -0.59
     withd
    -0.59
     wasteland
    -0.57
    should
    -0.57
     Photographer
    -0.56
     resc
    -0.56
     vacancy
    -0.56
     experiment
    -0.56
    POSITIVE LOGITS
     rid
    1.13
    TING
    1.06
    cloneembedreportprint
    0.97
     Started
    0.85
     notified
    0.83
    away
    0.81
     acquainted
    0.80
     Rid
    0.80
    chell
    0.78
    endar
    0.76
    Act Density 0.043%

    No Known Activations