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

    Neuronpedia

    INDEX
    Explanations

    wants, desires, or permissions expressed in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or want related to freedom and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.82
    livious
    -0.70
     enthusi
    -0.69
    ynski
    -0.62
    pher
    -0.60
     Echoes
    -0.53
    ility
    -0.53
    interstitial
    -0.52
     plur
    -0.51
    cling
    -0.51
    POSITIVE LOGITS
     without
    0.87
     WITHOUT
    0.80
     regardless
    0.80
     them
    0.77
     whenever
    0.73
    PLA
    0.70
    ktop
    0.70
    ably
    0.70
     wherever
    0.68
     to
    0.67
    Act Density 0.126%

    No Known Activations