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

    Neuronpedia

    INDEX
    Explanations

    words related to retractions or corrections

    oai_token-act-pair · gpt-3.5-turbo

    references to reactions or responses, particularly in political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eteria
    -0.70
    INESS
    -0.70
    ¬¼
    -0.69
    SHIP
    -0.66
    STEM
    -0.64
    WAYS
    -0.62
     similarities
    -0.62
     Awakens
    -0.62
    latest
    -0.61
    nuts
    -0.61
    POSITIVE LOGITS
    ainer
    1.06
    ribut
    1.00
    itled
    0.99
    arations
    0.97
    raction
    0.94
    rans
    0.91
    rog
    0.91
    upt
    0.91
    tell
    0.90
    reating
    0.89
    Act Density 0.008%

    No Known Activations