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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing emotional or impactful concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.81
    enhagen
    -0.72
    cript
    -0.71
    ringe
    -0.68
    sterdam
    -0.68
    beh
    -0.67
    epad
    -0.67
    pai
    -0.66
    nery
    -0.66
    pring
    -0.65
    POSITIVE LOGITS
     proportions
    0.96
     feats
    0.94
    ulously
    0.84
     pandemonium
    0.82
     unbeliev
    0.82
     feat
    0.80
     riches
    0.79
    ously
    0.79
    aneously
    0.77
     achievement
    0.75
    Act Density 5.685%

    No Known Activations