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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "do" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stakes
    -0.16
    @brief
    -0.15
     behalf
    -0.15
     dil
    -0.14
     Relation
    -0.14
    -tm
    -0.14
    ksam
    -0.14
    aki
    -0.14
    loom
    -0.13
    ncia
    -0.13
    POSITIVE LOGITS
    ffee
    0.18
     ÑģкладÑĥ
    0.18
    è¾¾
    0.17
    à¹ģม
    0.16
    DownList
    0.15
    .gstatic
    0.15
    gether
    0.15
    Argb
    0.14
    acent
    0.14
    ledo
    0.14
    Act Density 0.015%

    No Known Activations