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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "and," especially in contexts that relate to groups or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uga
    -0.17
    wards
    -0.15
    byt
    -0.14
     actionTypes
    -0.14
    ór
    -0.14
    948
    -0.13
    zz
    -0.13
    525
    -0.13
    ëŁī
    -0.13
    áš
    -0.13
    POSITIVE LOGITS
     crew
    0.20
     Crew
    0.15
    amu
    0.15
    uely
    0.15
    esson
    0.14
    chwitz
    0.14
    itsu
    0.14
    crew
    0.14
    emu
    0.14
     myself
    0.14
    Act Density 0.114%

    No Known Activations