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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a form of the verb 'to be'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    onal
    -0.82
    olid
    -0.72
    ysical
    -0.69
    CLOSE
    -0.67
    SHIP
    -0.65
     Frenzy
    -0.65
     convergence
    -0.65
    ammy
    -0.61
    ories
    -0.61
     Federation
    -0.59
    POSITIVE LOGITS
     admitted
    0.94
     confessed
    0.90
    é¾įåĸļ士
    0.87
     admits
    0.86
     acknowledged
    0.84
     penned
    0.84
     conceded
    0.79
     profess
    0.79
     testified
    0.76
     wrote
    0.76
    Act Density 0.034%

    No Known Activations