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

    Neuronpedia

    INDEX
    Explanations

    references to cracks and crack-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picchu
    -0.70
    цвета
    -0.54
    zev
    -0.51
     memu
    -0.50
    jooq
    -0.48
     вікі
    -0.47
    Geografi
    -0.47
    Edit
    -0.47
    يًا
    -0.47
     keren
    -0.47
    POSITIVE LOGITS
    })`
    0.68
    crack
    0.66
     crack
    0.66
    "])
    0.66
    resave
    0.65
     Ranger
    0.64
    kranz
    0.64
    ']],
    0.63
     COA
    0.63
     Barry
    0.62
    Act Density 2.302%

    No Known Activations