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

    Neuronpedia

    INDEX
    Explanations

    references to "inside" and "interior" concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HasKey
    -0.81
    CodeAttribute
    -0.75
     beret
    -0.70
     drept
    -0.69
    Geographie
    -0.69
    ">*
    -0.68
     تكبرها
    -0.68
     Crimean
    -0.67
    ه‌اند
    -0.67
    graphiques
    -0.67
    POSITIVE LOGITS
     Inside
    1.59
    Inside
    1.51
     inside
    1.49
     INSIDE
    1.42
    inside
    1.37
    INSIDE
    1.34
     InputDecoration
    1.12
     Inner
    1.07
     Dentro
    1.05
     insides
    1.00
    Act Density 0.101%

    No Known Activations