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

    Neuronpedia

    INDEX
    Explanations

    terms related to reconstruction processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumii
    -0.53
    VYMaps
    -0.52
    enumi
    -0.50
     szár
    -0.46
    Kjelder
    -0.46
     transférez
    -0.45
     الحره
    -0.45
     nahilalakip
    -0.45
     paille
    -0.45
     désolés
    -0.45
    POSITIVE LOGITS
     overlap
    0.64
     reconstruction
    0.59
     thickness
    0.58
     overlaps
    0.56
     overla
    0.51
     overlapped
    0.50
     leak
    0.49
     overlapping
    0.49
    overlap
    0.48
     leakage
    0.48
    Act Density 0.519%

    No Known Activations