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

    Neuronpedia

    INDEX
    Explanations

    references to tools or actions related to cooking or preparing food

    oai_token-act-pair · gpt-3.5-turbo

    references to food-related actions and pests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.86
    abies
    -0.83
    ote
    -0.83
    antics
    -0.80
    atics
    -0.80
    istered
    -0.79
    ittal
    -0.79
    alus
    -0.79
    obi
    -0.76
    otive
    -0.76
    POSITIVE LOGITS
     Hilton
    0.76
    âĸĪ
    0.76
     Torres
    0.70
    ername
    0.63
    ãĥ¼ãĥĨ
    0.62
     Clicker
    0.62
     witch
    0.62
     Debor
    0.60
    âĶĢâĶĢ
    0.60
     interstate
    0.59
    Act Density 0.087%

    No Known Activations