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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "leftover"

    oai_token-act-pair · gpt-3.5-turbo

    references to directional terms and sports terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.77
    ashtra
    -0.76
    antz
    -0.72
    mercial
    -0.71
    anut
    -0.70
    Ĥª
    -0.70
    Stat
    -0.70
    DragonMagazine
    -0.70
    nown
    -0.70
    sem
    -0.69
    POSITIVE LOGITS
     flank
    0.68
     circles
    0.66
     Makoto
    0.65
     pockets
    0.65
     throats
    0.65
    ovych
    0.64
     choke
    0.64
     footprints
    0.63
     slic
    0.62
    izabeth
    0.61
    Act Density 0.085%

    No Known Activations