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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs or phrases implying purpose or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kil
    -0.17
    fillType
    -0.15
    rum
    -0.15
    oader
    -0.14
    indsight
    -0.13
    oproject
    -0.13
    mium
    -0.13
    ãģ¤ãģij
    -0.13
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.13
    need
    -0.13
    POSITIVE LOGITS
    gether
    0.27
    /from
    0.26
    plevel
    0.25
    ogle
    0.21
    tem
    0.19
    /about
    0.18
    asting
    0.18
    ledo
    0.18
    pline
    0.17
    tems
    0.17
    Act Density 1.105%

    No Known Activations