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

    Neuronpedia

    INDEX
    Explanations

    phrases related to destruction and removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estimés
    -0.62
     createState
    -0.56
    stuck
    -0.54
    TemporalType
    -0.53
     GoogleFonts
    -0.53
    stdint
    -0.52
    IntoConstraints
    -0.50
     tempi
    -0.50
     createContext
    -0.50
     whereof
    -0.49
    POSITIVE LOGITS
     deleteUser
    0.91
     erase
    0.90
     eliminare
    0.89
     Erase
    0.88
    Elimin
    0.84
     disappear
    0.83
     elimination
    0.83
     elimin
    0.82
     eliminated
    0.82
     Elimination
    0.82
    Act Density 0.368%

    No Known Activations