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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¿Ļæł·çļĦ
    -0.14
    ãģĵãĤĵãģª
    -0.14
    ãģªãĤĵãģ¦
    -0.14
    नल
    -0.14
     æ¼
    -0.14
    VILLE
    -0.14
    лаÑģ
    -0.13
    Such
    -0.13
     such
    -0.13
     Afterwards
    -0.13
    POSITIVE LOGITS
     again
    0.24
    again
    0.24
     you
    0.21
     Again
    0.20
     candid
    0.20
     part
    0.19
     what
    0.19
     certainly
    0.18
     particularly
    0.18
    Again
    0.18
    Act Density 0.306%

    No Known Activations