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

    Neuronpedia

    INDEX
    Explanations

    words related to software programming or codes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "def" associated with definitions or definitions of terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wi
    -0.72
     Hudson
    -0.69
     Pap
    -0.65
     Herald
    -0.64
     Organization
    -0.62
     Tou
    -0.61
     Kath
    -0.61
     gallon
    -0.60
     Pilot
    -0.60
     inquire
    -0.59
    POSITIVE LOGITS
    def
    4.01
    Def
    2.31
    DEF
    2.02
     def
    1.84
    defense
    1.73
     Def
    1.72
     DEF
    1.46
    Defense
    1.29
     defence
    1.15
     defense
    1.11
    Act Density 0.017%

    No Known Activations