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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structure in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.50
    zies
    -0.47
    toEqual
    -0.46
    Examine
    -0.45
    |
    -0.45
    <eos>
    -0.44
    ForeignKey
    -0.44
    țiune
    -0.44
     hon
    -0.43
    .*
    -0.42
    POSITIVE LOGITS
    principalColumn
    0.88
    setupUi
    0.88
    SequentialGroup
    0.86
     Италијани
    0.84
    ConstraintMaker
    0.84
    RefNanny
    0.78
     Савезне
    0.78
    EndGlobal
    0.77
    ніципалі
    0.77
    awtextra
    0.75
    Act Density 0.005%

    No Known Activations