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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accomplishments and roles within academic or professional contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.75
     >=",
    -0.70
    Portale
    -0.69
    Datuak
    -0.69
     minimization
    -0.68
     maximization
    -0.67
     greateſt
    -0.67
     itſelf
    -0.66
     joaat
    -0.65
     كومونز
    -0.65
    POSITIVE LOGITS
     so
    0.58
     for
    0.51
     por
    0.50
     or
    0.50
    bower
    0.47
     pre
    0.46
     most
    0.45
     «
    0.45
     in
    0.44
     i
    0.42
    Act Density 0.434%

    No Known Activations