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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal or social relationships and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Y
    -0.46
    httphttps
    -0.45
    alk
    -0.45
    WriteBarrier
    -0.44
     Pres
    -0.44
     En
    -0.43
     actionMode
    -0.43
     Top
    -0.42
     T
    -0.42
     Val
    -0.42
    POSITIVE LOGITS
     avoient
    0.92
     aveug
    0.83
     religieuses
    0.82
     étoient
    0.82
     chrétien
    0.82
     stratégique
    0.82
     dégust
    0.82
     médié
    0.80
     alimentaire
    0.79
     mourut
    0.79
    Act Density 1.171%

    No Known Activations