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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "comm" followed by a high numeric value

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balk
    -0.76
    BOOK
    -0.68
     Dust
    -0.66
     Reconstruction
    -0.64
     Bloom
    -0.63
     Borderlands
    -0.63
    ting
    -0.62
     BDS
    -0.61
     Depression
    -0.61
     Zhu
    -0.61
    POSITIVE LOGITS
    onsense
    1.17
    ittal
    1.03
    ittees
    1.03
    comm
    1.02
    merce
    0.98
    ittee
    0.98
    puter
    0.97
    rontal
    0.95
    anded
    0.92
    ands
    0.92
    Act Density 0.003%

    No Known Activations