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

    Neuronpedia

    INDEX
    Explanations

    parameters related to UI element properties in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.73
    ↵
    -0.70
     “
    -0.61
    ,
    -0.56
    ↵↵
    -0.56
    .
    -0.53
     (
    -0.53
    qu
    -0.52
    ’
    -0.51
    <eos>
    -0.50
    POSITIVE LOGITS
    PreferredItem
    1.22
    Personendaten
    1.22
     صوتيه
    1.20
    ########.
    1.10
     propOrder
    1.06
     "..\..\..\
    1.04
    Hochspringen
    1.02
     виправивши
    1.02
    IntoConstraints
    1.02
     Roskov
    1.01
    Act Density 0.001%

    No Known Activations