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

    Neuronpedia

    INDEX
    Explanations

    terms and expressions related to organizational structures, processes, and formalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PLWABN
    -0.64
    enumi
    -0.62
     ويكيپيديا
    -0.60
     newBuilder
    -0.55
    nought
    -0.55
    igneur
    -0.53
    aile
    -0.53
    contentLoaded
    -0.53
     cherchés
    -0.52
    цездатний
    -0.51
    POSITIVE LOGITS
     Și
    1.03
     rumors
    0.99
     favors
    0.98
     favorably
    0.98
     marginalized
    0.98
     flavors
    0.97
    ized
    0.94
     behaviors
    0.93
     favoring
    0.93
    cozy
    0.93
    Act Density 0.567%

    No Known Activations