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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between different subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥį
    -0.17
    erez
    -0.16
    erland
    -0.15
    nock
    -0.15
    ksen
    -0.15
    achu
    -0.15
    ENTER
    -0.14
    EMPLARY
    -0.14
    elan
    -0.14
    neau
    -0.14
    POSITIVE LOGITS
     vice
    1.52
     Vice
    1.17
    vice
    1.15
     VP
    0.71
    VICE
    0.69
     Conversely
    0.57
     reverse
    0.56
     visa
    0.54
     ngược
    0.51
     versa
    0.50
    Act Density 0.092%

    No Known Activations