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
    50
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    end punctuation and pauses in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     switch
    -0.42
     Switch
    -0.40
    Smarty
    -0.39
    thwaite
    -0.38
    getDoctrine
    -0.37
     fertiliser
    -0.37
     swear
    -0.37
    iks
    -0.37
    Jeg
    -0.36
    Switch
    -0.36
    POSITIVE LOGITS
     kasarigan
    0.64
     transfieras
    0.53
    InstrumentedTest
    0.53
    LookAnd
    0.52
     desmotivaciones
    0.50
    ſelf
    0.48
    berdayakan
    0.47
     betweenstory
    0.47
    叶修
    0.47
    bibfield
    0.46
    Act Density 2.168%

    No Known Activations