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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with "You" and other expressions focusing on direct engagement or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IH
    -0.16
    uhe
    -0.15
    infeld
    -0.15
    _dispatcher
    -0.14
    SG
    -0.14
    rophic
    -0.14
     Knot
    -0.14
    alic
    -0.14
    ationship
    -0.14
     Beds
    -0.13
    POSITIVE LOGITS
     Edwards
    0.19
    warf
    0.17
    cki
    0.16
    ki
    0.16
    ÙĪÙĨ
    0.14
    unc
    0.14
    aat
    0.14
    zie
    0.14
    ativity
    0.13
    ãĥ¼ãĤº
    0.13
    Act Density 0.033%

    No Known Activations