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

    Neuronpedia

    INDEX
    Explanations

    words related to legislation, history, and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    esta
    -0.62
    prus
    -0.61
     paradise
    -0.60
    istor
    -0.59
    agra
    -0.58
    rame
    -0.56
    ode
    -0.55
     stew
    -0.55
    itta
    -0.54
     dormant
    -0.54
    POSITIVE LOGITS
     whatsoever
    0.83
    _.
    0.82
     imaginable
    0.75
     thereafter
    0.72
     intervals
    0.72
    ..................
    0.72
    enance
    0.71
     srfAttach
    0.71
     ILCS
    0.70
    lust
    0.68
    Act Density 0.494%

    No Known Activations