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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of disbelief or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.63
    CloseOperation
    -0.62
    EndInit
    -0.62
     disambiguazione
    -0.56
    SBATCH
    -0.55
    --]
    -0.53
     Autorizaciones
    -0.51
    DockStyle
    -0.51
     initComponents
    -0.51
     pilota
    -0.50
    POSITIVE LOGITS
    atschappij
    0.58
    fulness
    0.56
     trouverez
    0.53
     quegli
    0.53
     inalámb
    0.53
     asiatique
    0.52
    uestamente
    0.52
    ivably
    0.51
     nécessairement
    0.49
     itſelf
    0.49
    Act Density 0.311%

    No Known Activations