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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to movement or progression

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uably
    -0.70
    annot
    -0.66
    Avg
    -0.66
    æ©Ł
    -0.65
    yrinth
    -0.64
    Wan
    -0.64
    quickShipAvailable
    -0.64
    uilt
    -0.62
    ãĥİ
    -0.59
    atched
    -0.57
    POSITIVE LOGITS
     oneself
    0.88
     anything
    0.84
    uate
    0.81
     anytime
    0.80
     anymore
    0.78
    enance
    0.74
     any
    0.73
    dress
    0.72
     unless
    0.71
     them
    0.70
    Act Density 0.440%

    No Known Activations