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
    70
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    elements related to narrative structure, particularly focusing on endings and conclusions in stories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.56
    Hochspringen
    -0.47
     AssemblyCulture
    -0.46
    Smarty
    -0.45
    frastructure
    -0.44
     TextAppearance
    -0.43
    $_['
    -0.43
    estacks
    -0.43
     Notion
    -0.43
     bani
    -0.42
    POSITIVE LOGITS
     ending
    0.56
    
    0.55
     avsl
    0.48
    principalTable
    0.47
     endings
    0.47
    efois
    0.46
     ends
    0.45
     FINAL
    0.45
     پایان
    0.45
     concluding
    0.45
    Act Density 0.001%

    No Known Activations