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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to various topics or updates, possibly related to news or information

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "this" and "that," indicating emphasis on specific points or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geons
    -0.85
    poon
    -0.74
    »Ĵ
    -0.73
    ARB
    -0.70
    onym
    -0.70
    Reader
    -0.68
    plets
    -0.68
    izont
    -0.66
    oru
    -0.65
    geon
    -0.65
    POSITIVE LOGITS
     fuss
    1.14
     stuff
    1.09
     nonsense
    1.02
     crap
    0.96
     mayhem
    0.96
     jazz
    0.96
     transpired
    0.94
     mattered
    0.93
     chatter
    0.93
     entails
    0.92
    Act Density 0.073%

    No Known Activations