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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods, which indicate the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¸
    -0.15
     River
    -0.15
    uron
    -0.14
     Thor
    -0.14
    agh
    -0.14
    lang
    -0.14
    vä
    -0.14
    LK
    -0.13
    mpi
    -0.13
     Kear
    -0.13
    POSITIVE LOGITS
     Garc
    0.19
    czy
    0.17
    WXYZ
    0.16
    mium
    0.15
    dsl
    0.14
    ATERIAL
    0.14
    eview
    0.14
    erator
    0.14
    annabin
    0.14
     PAR
    0.14
    Act Density 0.004%

    No Known Activations