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

    Neuronpedia

    INDEX
    Explanations

    terms related to creative works or artworks

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antha
    -0.86
    cffff
    -0.81
     Rohing
    -0.81
    wcs
    -0.78
     Adin
    -0.78
     Ukrain
    -0.76
    EStream
    -0.72
     blockers
    -0.72
     constitu
    -0.72
     todd
    -0.70
    POSITIVE LOGITS
    hops
    1.37
    paces
    1.15
    flows
    1.11
    station
    1.01
    works
    0.95
    fare
    0.94
    heet
    0.94
    bench
    0.93
    pace
    0.89
    hirt
    0.87
    Act Density 0.059%

    No Known Activations