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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and integer values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Autorizaciones
    -0.60
     betweenstory
    -0.51
    AnchorTagHelper
    -0.50
     activité
    -0.48
     iconLine
    -0.47
     dignité
    -0.47
     renang
    -0.45
     ilustracja
    -0.45
    kių
    -0.44
    ambilan
    -0.44
    POSITIVE LOGITS
    int
    1.53
     int
    0.94
    INT
    0.94
    ink
    0.70
    medium
    0.50
    ∫
    0.48
    SBATCH
    0.48
    ntk
    0.47
     שוליים
    0.47
    iint
    0.47
    Act Density 0.200%

    No Known Activations