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

    Neuronpedia

    INDEX
    Explanations

    words that emphasize change or progress

    oai_token-act-pair · gemini-2.0-flash

    the act of picking

    np_token-act-pair-logits · gpt-4o-mini

    pick

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     houſe
    -0.72
     Efq
    -0.68
     ſch
    -0.68
     étanche
    -0.66
     Monfieur
    -0.63
     quæ
    -0.63
     beſt
    -0.62
     iſt
    -0.62
     Eſ
    -0.61
    onViewCreated
    -0.61
    POSITIVE LOGITS
     picked
    1.27
     picking
    1.25
     pick
    1.23
     Picking
    1.15
     picks
    1.11
     PICK
    1.10
     pickup
    1.05
     Pick
    1.05
    pick
    1.04
    Picking
    1.03
    Act Density 2.977%

    No Known Activations