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

    Neuronpedia

    INDEX
    Explanations

    references to personal history and the implications of past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    goog
    -0.16
    ÅĻÃŃd
    -0.16
    elage
    -0.15
     serial
    -0.15
     sling
    -0.15
     functional
    -0.14
    itler
    -0.14
    nel
    -0.14
     tear
    -0.13
     DIM
    -0.13
    POSITIVE LOGITS
    ży
    0.15
    ики
    0.15
    ARS
    0.14
    AccessException
    0.14
    viso
    0.14
    adx
    0.14
    UBLISH
    0.14
    sil
    0.14
     saturn
    0.14
     Stout
    0.14
    Act Density 0.009%

    No Known Activations