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

    Neuronpedia

    INDEX
    Explanations

    dates in the format 'YYYY' occurring in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     himo
    -0.85
     Ceinture
    -0.67
     arrivant
    -0.67
     appuy
    -0.67
     Mémoires
    -0.66
     règlement
    -0.65
    nowu
    -0.64
     règne
    -0.63
     MediatR
    -0.63
     FBref
    -0.63
    POSITIVE LOGITS
     maneu
    0.84
     reluct
    0.78
     disagre
    0.78
     apprehen
    0.74
     encomp
    0.72
    which
    0.72
     disad
    0.70
     ineffec
    0.69
     shenan
    0.68
     inev
    0.68
    Act Density 0.167%

    No Known Activations