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

    Neuronpedia

    INDEX
    Explanations

    phrases related to testing or evaluating situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating political opportunities or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĸĪ
    -0.68
     shitty
    -0.67
     beautiful
    -0.65
     Ended
    -0.64
    Liter
    -0.64
    âĹ¼
    -0.63
     nudity
    -0.62
     photography
    -0.62
     XY
    -0.60
     sweats
    -0.59
    POSITIVE LOGITS
     reconsider
    0.84
     embold
    0.84
     rethink
    0.83
     recons
    0.82
    ansky
    0.80
     revis
    0.78
     resurg
    0.78
     recapt
    0.76
     2019
    0.74
     embattled
    0.72
    Act Density 0.986%

    No Known Activations