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

    Neuronpedia

    INDEX
    Explanations

    statements that challenge prevailing truths or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.65
     FORUM
    -0.46
     Astrophysical
    -0.44
    untos
    -0.44
    forder
    -0.43
     graph
    -0.41
    ColumnHeaders
    -0.40
     Graph
    -0.40
     ress
    -0.40
     mains
    -0.40
    POSITIVE LOGITS
    ⓧ
    0.72
    httphttps
    0.69
    ыгана
    0.69
    makeText
    0.66
     sauvages
    0.65
     שוליים
    0.64
    AxisAlignment
    0.63
    voyez
    0.63
     assoluto
    0.63
     nakalista
    0.61
    Act Density 0.277%

    No Known Activations