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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "complicit" or variations of it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -0.82
     intersper
    -0.75
     underval
    -0.75
     horrend
    -0.73
     miscon
    -0.68
     indestru
    -0.68
     disgra
    -0.68
     reluct
    -0.64
     fucker
    -0.63
     endow
    -0.63
    POSITIVE LOGITS
     Comp
    1.25
     comp
    1.20
     COMP
    1.15
    comp
    1.14
    Comp
    1.14
    COMP
    1.07
    komp
    0.88
     komp
    0.87
     compaction
    0.86
     COM
    0.83
    Act Density 0.096%

    No Known Activations