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

    Neuronpedia

    INDEX
    Explanations

    references to various locations within a country

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "country" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    char
    -0.79
    hod
    -0.72
    Lua
    -0.65
    riv
    -0.65
    omorph
    -0.64
    Module
    -0.63
    zes
    -0.63
     Priv
    -0.62
    asma
    -0.62
     RIS
    -0.62
    POSITIVE LOGITS
    wide
    0.94
     skyline
    0.74
     converge
    0.74
    ADA
    0.73
    keyes
    0.73
     illegally
    0.71
    hurst
    0.69
    arcer
    0.67
     waterways
    0.67
    ESE
    0.64
    Act Density 0.040%

    No Known Activations