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

    Neuronpedia

    INDEX
    Explanations

    words related to specific cultural or linguistic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sahara
    -0.17
     Reno
    -0.16
    hetto
    -0.15
     Martins
    -0.15
    ulo
    -0.15
    ÙĤÙĬØ©
    -0.14
     Desert
    -0.14
    139
    -0.14
     Staten
    -0.14
     Mong
    -0.14
    POSITIVE LOGITS
     Maya
    0.31
     Guatemala
    0.24
     Belize
    0.24
     Jaguar
    0.23
    mayan
    0.23
    atemala
    0.20
     Honduras
    0.20
     jade
    0.17
     glyphs
    0.17
    maya
    0.17
    Act Density 0.007%

    No Known Activations