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

    Neuronpedia

    INDEX
    Explanations

    phrases related to food and cuisine

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ously
    -0.73
     laundry
    -0.60
    HL
    -0.59
     makeup
    -0.58
    pace
    -0.58
    opher
    -0.57
    :]
    -0.56
     preference
    -0.55
    entials
    -0.55
    iggle
    -0.54
    POSITIVE LOGITS
    _-
    1.79
    webkit
    1.00
    =-=-=-=-=-=-=-=-
    0.95
    =-=-=-=-
    0.85
     [|
    0.78
    âĸº
    0.73
    sama
    0.72
    £
    0.72
    /-
    0.71
    âĢ¢âĢ¢
    0.69
    Act Density 0.089%

    No Known Activations