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

    Neuronpedia

    INDEX
    Explanations

    words that are homophones or closely related to "so"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     innocence
    -0.65
    theless
    -0.62
     misconception
    -0.62
     envy
    -0.60
     royalty
    -0.59
    DERR
    -0.59
     resemblance
    -0.58
     aristocracy
    -0.57
     FAA
    -0.57
     appeal
    -0.57
    POSITIVE LOGITS
    ppy
    1.19
    bered
    1.15
    vere
    1.14
    oths
    1.13
    pp
    1.09
    fter
    1.09
    pping
    1.09
    FTWARE
    1.09
    aring
    1.08
    aked
    1.07
    Act Density 0.042%

    No Known Activations