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

    Neuronpedia

    INDEX
    Explanations

    references to different villages and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.17
    astle
    -0.15
    /pay
    -0.14
    naissance
    -0.14
    _cls
    -0.14
    urgy
    -0.14
    .ZERO
    -0.14
     Counties
    -0.14
    orage
    -0.14
    74
    -0.14
    POSITIVE LOGITS
    ois
    0.22
    -wide
    0.20
     square
    0.20
    wide
    0.20
    -scale
    0.19
    -state
    0.19
    /state
    0.19
    -level
    0.18
     elders
    0.18
     hall
    0.18
    Act Density 0.021%

    No Known Activations