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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or teamwork in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rong
    -0.18
    omid
    -0.17
    enthal
    -0.16
    rosso
    -0.16
    uo
    -0.15
    ould
    -0.15
    ooks
    -0.14
    isay
    -0.14
    abb
    -0.14
    iek
    -0.14
    POSITIVE LOGITS
    odox
    0.15
     kali
    0.15
    074
    0.14
     Doe
    0.14
    )this
    0.14
     CP
    0.13
    901
    0.13
     conven
    0.13
    Principal
    0.13
     Burgess
    0.13
    Act Density 0.222%

    No Known Activations