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

    Neuronpedia

    INDEX
    Explanations

    phrases that express perceptions, evaluations, or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     أجل
    -0.66
     Alexei
    -0.63
     sobran
    -0.60
     Alexey
    -0.60
     quên
    -0.60
    первых
    -0.59
    mogat
    -0.59
     eksper
    -0.58
     πριν
    -0.57
    latego
    -0.56
    POSITIVE LOGITS
     regarded
    1.08
     treated
    0.93
     viewed
    0.92
     Treated
    0.82
     Viewed
    0.80
     treating
    0.80
     trataba
    0.76
    Treating
    0.75
     considéré
    0.70
    treated
    0.69
    Act Density 0.341%

    No Known Activations