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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty about future outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PC
    -0.15
    ipur
    -0.14
    deniz
    -0.14
    gia
    -0.14
    ars
    -0.14
    esinden
    -0.13
    Au
    -0.13
    Miller
    -0.13
    chart
    -0.13
     Darling
    -0.13
    POSITIVE LOGITS
    ertz
    0.15
    aging
    0.15
    poster
    0.15
    AGING
    0.15
    mpi
    0.15
    evin
    0.14
    stell
    0.14
     пн
    0.14
     Tracks
    0.14
    ÑĢож
    0.14
    Act Density 0.016%

    No Known Activations