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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç·Ĵ
    -0.16
     best
    -0.15
    889
    -0.15
    enza
    -0.14
    ocha
    -0.14
    919
    -0.14
    çķª
    -0.14
    panse
    -0.14
    ism
    -0.14
    944
    -0.14
    POSITIVE LOGITS
    igator
    0.16
    иÑĩа
    0.15
    arten
    0.14
    asaki
    0.14
    readcr
    0.14
    ataka
    0.14
    ÑĥÑģка
    0.14
    quirrel
    0.14
    ouser
    0.14
    alama
    0.14
    Act Density 0.027%

    No Known Activations