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

    Neuronpedia

    INDEX
    Explanations

    conjunctions indicating contrast or exception

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rine
    -0.86
     compréhen
    -0.73
     délib
    -0.72
     Ruman
    -0.70
     appréci
    -0.69
     légitime
    -0.68
     Timp
    -0.67
    mycompany
    -0.67
     réaliste
    -0.66
     Kalis
    -0.65
    POSITIVE LOGITS
     however
    0.69
    however
    0.64
     infarction
    0.55
    lably
    0.52
     nė
    0.52
     apetito
    0.51
     valsty
    0.50
    rehensive
    0.50
     doPost
    0.50
    riction
    0.49
    Act Density 0.040%

    No Known Activations