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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unexpected or emotional experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of feelings or emotions related to experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.91
    currently
    -0.87
    prus
    -0.80
    apons
    -0.75
    aka
    -0.74
    quartered
    -0.72
    ignty
    -0.72
    objects
    -0.72
    krit
    -0.72
    often
    -0.70
    POSITIVE LOGITS
     raining
    0.99
     downhill
    0.92
     pandemonium
    0.76
     abrupt
    0.74
     unintentional
    0.74
     uphill
    0.74
     surreal
    0.73
     spur
    0.73
     pleasant
    0.72
     fitting
    0.72
    Act Density 0.400%

    No Known Activations