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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quality or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umpt
    -0.19
     beyond
    -0.16
    rary
    -0.15
    eru
    -0.15
     crim
    -0.14
    ayi
    -0.14
    ocking
    -0.14
    ays
    -0.14
     Canary
    -0.14
    stag
    -0.14
    POSITIVE LOGITS
    than
    0.16
     than
    0.15
    iki
    0.15
    ãĤ¸ãĤª
    0.15
    eref
    0.14
    ighthouse
    0.14
    dynamic
    0.14
     atol
    0.14
    IGIN
    0.14
    igi
    0.14
    Act Density 0.065%

    No Known Activations