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

    Neuronpedia

    INDEX
    Explanations

    descriptors of behavior and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    createNewFile
    -0.40
     communautaire
    -0.28
     requ
    -0.28
    bní
    -0.26
     conjun
    -0.25
     công
    -0.24
    adilan
    -0.23
     적
    -0.22
     bienvenue
    -0.22
     dostęp
    -0.22
    POSITIVE LOGITS
     habits
    0.80
     Habits
    0.77
     ddelweddau
    0.71
     habit
    0.69
     Gesture
    0.69
     FetchType
    0.68
     Behaviors
    0.68
     gestures
    0.67
     behaviors
    0.66
     gestos
    0.66
    Act Density 0.299%

    No Known Activations