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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate announcements or significant updates regarding products, particularly in the context of new motorcycle models

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    expandindo
    -0.75
     propOrder
    -0.72
     femininas
    -0.69
    ########.
    -0.69
     InputDecoration
    -0.68
    ungkinan
    -0.66
     normaux
    -0.65
     समीक्षक
    -0.64
     onOptions
    -0.63
     esternos
    -0.63
    POSITIVE LOGITS
    hint
    0.65
     surprises
    0.57
     surprise
    0.56
     secrets
    0.56
     secret
    0.56
     reveal
    0.54
    🤫
    0.54
     unveil
    0.54
     revealed
    0.52
     hinted
    0.51
    Act Density 0.095%

    No Known Activations