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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "combine" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampa
    -0.15
    lash
    -0.15
    ει
    -0.14
    ิà¹Ī
    -0.14
    _MEDIUM
    -0.14
    antha
    -0.14
    uran
    -0.14
    indh
    -0.14
    Ñĥж
    -0.14
    eler
    -0.14
    POSITIVE LOGITS
    tures
    0.18
    -sama
    0.17
    mlink
    0.15
    pcf
    0.15
     nÄĥ
    0.14
     with
    0.14
    ô
    0.14
     Berm
    0.14
    çĽĸ
    0.14
    wealth
    0.14
    Act Density 0.031%

    No Known Activations