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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of community or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.18
    deo
    -0.16
    inea
    -0.15
    aign
    -0.15
     Waters
    -0.15
     Kits
    -0.15
     Mim
    -0.14
    ullet
    -0.14
     gem
    -0.14
    inder
    -0.13
    POSITIVE LOGITS
    ionales
    0.16
     themselves
    0.16
    iversit
    0.15
     bunch
    0.15
    agrams
    0.15
    覧
    0.15
    /problems
    0.15
     yourselves
    0.14
    oval
    0.14
     Ñģами
    0.14
    Act Density 0.115%

    No Known Activations