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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their repetitions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dÃŃ
    -0.15
    leDb
    -0.15
     Liberation
    -0.15
    crap
    -0.14
    zens
    -0.14
    oll
    -0.14
     Lamp
    -0.14
    erland
    -0.14
    θεν
    -0.14
    qid
    -0.14
    POSITIVE LOGITS
    enberg
    0.17
    ADS
    0.16
    bury
    0.16
    erno
    0.15
     loos
    0.15
    ekt
    0.15
    108
    0.14
    antas
    0.14
    ìĪĺ
    0.14
    ipy
    0.14
    Act Density 0.248%

    No Known Activations