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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "plug" or phrases related to devices being connected

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     alkoh
    -0.81
     kriminal
    -0.79
     panik
    -0.77
     kaos
    -0.75
     seksi
    -0.72
     kosme
    -0.72
     konserv
    -0.70
     kooper
    -0.70
     karton
    -0.69
     radikal
    -0.68
    POSITIVE LOGITS
     plug
    1.63
     plugs
    1.47
    plug
    1.44
     Plug
    1.41
     plugged
    1.32
     plugin
    1.30
    Plug
    1.30
     plugging
    1.29
    plugs
    1.25
     PLUG
    1.22
    Act Density 0.079%

    No Known Activations