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

    Neuronpedia

    INDEX
    Explanations

    automobile-related terms

    oai_token-act-pair · gpt-3.5-turbo

    sports and physical activity-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥī
    -0.82
    ãĤ¨ãĥ«
    -0.82
    Benz
    -0.81
    URA
    -0.78
    Products
    -0.75
    é¾įå
    -0.74
    Tok
    -0.74
    Grade
    -0.71
    Pres
    -0.71
    Pages
    -0.71
    POSITIVE LOGITS
     extraord
    1.15
    hers
    0.84
    chers
    0.81
     fallacy
    0.78
     syndrome
    0.78
    agers
    0.77
    er
    0.76
    orer
    0.76
    cher
    0.75
    rosis
    0.72
    Act Density 0.448%

    No Known Activations