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

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    80
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words related to email functionality and communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.32
     bijzonder
    -0.31
     giudi
    -0.29
     larger
    -0.28
     Erklärung
    -0.28
     very
    -0.26
     semplicemente
    -0.26
     voeten
    -0.26
     improvement
    -0.26
     évaluations
    -0.25
    POSITIVE LOGITS
     smtplib
    0.92
    PMailer
    0.90
    MLLoader
    0.87
    0.81
     propOrder
    0.73
    хьтан
    0.70
     mails
    0.70
    uxxxx
    0.69
     للاسماء
    0.69
    parsedMessage
    0.69
    Act Density 0.041%

    No Known Activations