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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    recurring mentions of "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Iterator
    -0.78
    verb
    -0.70
    amera
    -0.70
    anova
    -0.70
    axter
    -0.69
    cam
    -0.69
    wcsstore
    -0.65
    numbered
    -0.64
    /-
    -0.63
    milo
    -0.63
    POSITIVE LOGITS
     midst
    1.04
     Philippines
    1.01
     periphery
    0.99
     aftermath
    0.98
     entirety
    0.96
     guise
    0.95
     Balkans
    0.94
     workplace
    0.92
     Netherlands
    0.90
     nation
    0.90
    Act Density 0.400%

    No Known Activations