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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lack of appreciation or recognition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking things for granted and the concept of free access or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tained
    -0.82
    Constructed
    -0.77
    allowed
    -0.72
    apple
    -0.70
    legate
    -0.70
    wra
    -0.70
    pri
    -0.66
     Riders
    -0.66
    hao
    -0.65
    mare
    -0.65
    POSITIVE LOGITS
     ILCS
    0.69
     sake
    0.68
     imagin
    0.65
     Skydragon
    0.65
     blush
    0.63
     reasons
    0.62
     grin
    0.62
    Ø©
    0.61
     enc
    0.59
     credits
    0.58
    Act Density 0.075%

    No Known Activations