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

    Neuronpedia

    INDEX
    Explanations

    language related to habits and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vla
    -0.14
     Pell
    -0.13
    gon
    -0.13
    adele
    -0.13
    lg
    -0.13
    æºĢ
    -0.13
    alom
    -0.13
    pool
    -0.13
    hash
    -0.13
     puss
    -0.13
    POSITIVE LOGITS
     habit
    0.76
     habits
    0.75
     Hab
    0.73
     Habit
    0.64
     hab
    0.62
    hab
    0.60
    habit
    0.59
    ä¹ł
    0.57
     habitual
    0.50
    ç¿Ĵ
    0.50
    Act Density 0.163%

    No Known Activations