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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "prepared" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.50
     ciudadanía
    -0.46
     istrinya
    -0.46
     suaminya
    -0.46
     infierno
    -0.45
     prisonniers
    -0.45
     enfans
    -0.45
     Stücke
    -0.45
     sustancia
    -0.44
     vuestros
    -0.43
    POSITIVE LOGITS
     prepared
    1.95
    prepared
    1.81
     prepare
    1.77
     Prepared
    1.70
    Prepared
    1.63
    prepare
    1.57
     Prepare
    1.55
     prepares
    1.54
    Prepare
    1.45
     prepar
    1.42
    Act Density 0.207%

    No Known Activations