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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "what do" followed by certain phrases or terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.74
    /**
    -0.72
    ⓧ
    -0.70
    
    -0.68
     inaugurate
    -0.60
     AssemblyCompany
    -0.57
    bardziej
    -0.56
    /*
    -0.56
     endow
    -0.55
     ajudá
    -0.55
    POSITIVE LOGITS
     Minang
    1.01
     bandung
    0.96
     lele
    0.93
     majest
    0.90
     loto
    0.90
     karton
    0.89
     utop
    0.87
     ohr
    0.86
     gubern
    0.84
     laci
    0.84
    Act Density 0.507%

    No Known Activations