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

    Neuronpedia

    INDEX
    Explanations

    mentions of complaints or complicated issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complaint" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.79
    selection
    -0.78
    bill
    -0.76
    ctors
    -0.75
    »Ĵ
    -0.74
    doors
    -0.73
    plane
    -0.70
    ggies
    -0.70
    hyde
    -0.69
     garlic
    -0.68
    POSITIVE LOGITS
     Compl
    1.14
    Compl
    0.90
    icit
    0.86
    aints
    0.83
    aint
    0.81
    ustration
    0.79
    ications
    0.79
    icated
    0.78
    acent
    0.77
     Puzz
    0.77
    Act Density 0.009%

    No Known Activations