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

    Neuronpedia

    INDEX
    Explanations

    keywords related to complaints or complaints being made

    oai_token-act-pair · gpt-3.5-turbo

    instances of people expressing dissatisfaction or grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.65
    tein
    -0.65
    assisted
    -0.63
    ãĥĥãĤ¯
    -0.63
    arnaev
    -0.63
    ifter
    -0.61
     ILCS
    -0.59
    ãĥ¯
    -0.58
    illary
    -0.58
     Manson
    -0.57
    POSITIVE LOGITS
     bitterly
    1.30
     loudly
    1.24
     angrily
    0.91
     aloud
    0.90
     incess
    0.87
     about
    0.85
     vehemently
    0.84
     against
    0.82
     complaining
    0.81
    isance
    0.80
    Act Density 0.034%

    No Known Activations