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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating accompaniment or connection between elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _AF
    -0.15
    ibs
    -0.14
    objs
    -0.14
    oment
    -0.14
    lyph
    -0.14
    GRP
    -0.14
     Clement
    -0.14
     both
    -0.13
    urgy
    -0.13
     Oak
    -0.13
    POSITIVE LOGITS
     accompany
    0.20
     accompanies
    0.18
     accompanying
    0.18
    ä¸Ģèµ·
    0.17
    oppable
    0.17
    omes
    0.16
    alar
    0.15
    ome
    0.15
    usu
    0.14
    ظÙĬÙģ
    0.14
    Act Density 0.097%

    No Known Activations