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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference the concept of "the scheme of things."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.73
    onto
    -0.62
    favorite
    -0.62
    bush
    -0.61
    arat
    -0.60
    erella
    -0.59
    lessly
    -0.59
    illy
    -0.58
     Ahead
    -0.57
    obyl
    -0.57
    POSITIVE LOGITS
    pires
    0.77
     hindsight
    0.72
     mortals
    0.69
     unbeliev
    0.69
     shenan
    0.67
    Ŀ
    0.65
     things
    0.62
    æĢ
    0.59
     beh
    0.58
    URES
    0.56
    Act Density 0.038%

    No Known Activations