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

    Neuronpedia

    INDEX
    Explanations

    references to stylistic elements and physical attributes associated with various items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃst
    -0.17
    ιÏĥÏĦή
    -0.15
    estring
    -0.15
    nds
    -0.15
    adoo
    -0.15
    nees
    -0.15
    istrat
    -0.14
    anean
    -0.14
    aking
    -0.14
    aversable
    -0.14
    POSITIVE LOGITS
     Sm
    0.54
    sm
    0.51
     sm
    0.51
    Sm
    0.50
    -sm
    0.46
     SM
    0.46
    SM
    0.45
    _sm
    0.45
    .sm
    0.44
    (sm
    0.43
    Act Density 0.025%

    No Known Activations