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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¼ĺ
    -0.18
    -ÑĤо
    -0.17
    sel
    -0.16
    iye
    -0.16
    ãĥ
    -0.15
    dle
    -0.15
    ITTER
    -0.15
    ähl
    -0.15
    arden
    -0.15
    ye
    -0.14
    POSITIVE LOGITS
    ivec
    0.17
    icut
    0.17
    ative
    0.16
    tures
    0.16
    IGHL
    0.16
     encount
    0.14
    rium
    0.14
     with
    0.14
    inger
    0.14
    -sama
    0.14
    Act Density 0.034%

    No Known Activations