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

    Neuronpedia

    INDEX
    Explanations

    references to actions and activities carried out by individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    —-
    -0.65
    ensing
    -0.65
    etting
    -0.64
     prosecuting
    -0.64
    ocus
    -0.63
     fray
    -0.62
    AU
    -0.61
     Voters
    -0.59
    iaz
    -0.58
    oyer
    -0.58
    POSITIVE LOGITS
     been
    1.31
     undergone
    1.18
    been
    1.12
     gotten
    1.03
     access
    0.98
     gone
    0.95
     Been
    0.93
     eaten
    0.91
    kell
    0.89
     recourse
    0.89
    Act Density 0.352%

    No Known Activations