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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific concept or identity termed "lone", especially in association with individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.88
    lished
    -0.88
    ulate
    -0.82
    andise
    -0.81
    abulary
    -0.81
    encies
    -0.77
    ulated
    -0.76
    enegger
    -0.75
    ulative
    -0.74
    ropri
    -0.74
    POSITIVE LOGITS
     wolf
    1.06
     wolves
    0.91
    eteen
    0.81
    istic
    0.80
     lone
    0.79
     ranger
    0.79
     Swordsman
    0.79
     exception
    0.78
    volent
    0.78
     traveler
    0.75
    Act Density 0.031%

    No Known Activations