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

    Neuronpedia

    INDEX
    Explanations

    references to group activities and social dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.74
     preſent
    -0.63
     fevere
    -0.63
     uſed
    -0.63
     houſe
    -0.61
     fubject
    -0.61
     ſy
    -0.60
     purpoſe
    -0.60
     Chriftian
    -0.60
     prefent
    -0.59
    POSITIVE LOGITS
     nahilalakip
    0.67
    iastical
    0.56
    laceae
    0.52
    apnews
    0.51
    Vidite
    0.50
     letter
    0.49
     visa
    0.49
     Samuels
    0.48
     Ve
    0.47
    zler
    0.47
    Act Density 0.036%

    No Known Activations